{
  "schemaVersion": "1.0",
  "item": {
    "slug": "snipara-mcp",
    "name": "Snipara Mcp",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/alopez3006/snipara-mcp",
    "canonicalUrl": "https://clawhub.ai/alopez3006/snipara-mcp",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/snipara-mcp",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=snipara-mcp",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "pyproject.toml",
      "skill.md",
      "src/snipara_mcp/__init__.py",
      "src/snipara_mcp/auth.py",
      "src/snipara_mcp/rlm_tools.py"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-07T17:22:31.273Z",
      "expiresAt": "2026-05-14T17:22:31.273Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
        "contentDisposition": "attachment; filename=\"afrexai-annual-report-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/snipara-mcp"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/snipara-mcp",
    "agentPageUrl": "https://openagent3.xyz/skills/snipara-mcp/agent",
    "manifestUrl": "https://openagent3.xyz/skills/snipara-mcp/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/snipara-mcp/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "System Instructions for AI Agents",
        "body": "You are an AI assistant with access to Snipara MCP tools. Use these tools to provide faster, more accurate answers by querying pre-indexed documentation instead of reading files one-by-one."
      },
      {
        "title": "When to Use Snipara Tools",
        "body": "✅ USE Snipara when:\n\nUser asks \"How does X work?\" → Use rlm_ask or rlm_context_query\nUser asks \"Where do we do X?\" → Use rlm_multi_project_query (if Team plan)\nUser asks \"What are my preferences?\" → Use rlm_recall\nYou need to find code patterns across multiple repos\nYou need to understand architecture/documentation\n\n❌ DON'T use Snipara when:\n\nUser asks you to read a SPECIFIC file they named → Use native Read tool\nUser asks you to edit/write code → Use native Edit/Write tools\nUser asks to run commands → Use native Bash tool\nSnipara API returns error → Fall back to native tools"
      },
      {
        "title": "Recommended Workflow",
        "body": "First query: Always start with rlm_ask (fast, works on Free plan)\nIf not found: Try rlm_context_query with search_mode: \"semantic\" (requires Pro)\nMulti-repo search: Use rlm_multi_project_query if user has Team plan\nRemember decisions: Use rlm_remember to store important info for future sessions"
      },
      {
        "title": "Error Handling",
        "body": "If Snipara returns an error:\n\nCheck if user has required plan (Free/Pro/Team)\nCheck if docs are indexed (user needs to upload to dashboard first)\nFall back to native Read/Grep/Glob tools\nExplain to user what went wrong and suggest solution"
      },
      {
        "title": "Example Usage",
        "body": "User: \"How does our authentication system work?\"\n\nGood response:\n1. Call rlm_ask(\"authentication system\")\n2. Get relevant docs in 2 seconds\n3. Synthesize answer from returned context\n\nBad response:\n1. Use Grep to search for \"auth\"\n2. Read 10 files sequentially\n3. Hit token limits\n4. Give incomplete answer"
      },
      {
        "title": "The Problem You Have Right Now",
        "body": "Your AI assistant searches files one-by-one using grep/find. With large codebases:\n\n❌ Queries take 20+ seconds\n❌ AI reads 50K tokens to answer simple questions\n❌ You manually search 5 repos to find \"how we do X\"\n❌ AI forgets your preferences next session"
      },
      {
        "title": "The Solution (30 seconds from now)",
        "body": "# 1. Install\npip install snipara-mcp   # Python\nnpm install snipara-mcp   # Node.js\n\n# 2. Get your API key\n# Sign up at https://snipara.com (Free: 100 queries/month)\n\n# 3. Set environment variable\nexport SNIPARA_API_KEY=\"your-key-here\"\n\n# 4. Add to your MCP client (Claude Code, Cline, Roo Code, etc.)\n# Done! Start using rlm_ask() in your next chat"
      },
      {
        "title": "Your First Query (Try This Now)",
        "body": "You: \"How does authentication work in my codebase?\"\n\nBehind the scenes:\n  rlm_context_query(\"authentication\")\n  → 2 seconds later\n  → Returns top 3 relevant docs (3K tokens instead of 50K)\n\nResult: Instant, accurate answer\n\nNote: Before querying, index your docs at https://snipara.com/dashboard (upload .md/.txt/.mdx files)."
      },
      {
        "title": "🎯 Quick Answers (Start Here)",
        "body": "Plan Required: ✅ FREE (100 queries/mo)\n\nTool: rlm_ask\nUse when: You need a fast answer from your docs\nExample: rlm_ask(\"API rate limits\")\nTime saved: 20 seconds → 2 seconds per query\n\n{ \"query\": \"How do we handle webhooks?\" }"
      },
      {
        "title": "🔍 Deep Research (Complex Questions)",
        "body": "Plan Required: ✅ FREE (keyword only) | 🔥 PRO ($19/mo for semantic)\n\nTool: rlm_context_query\nUse when: You need semantic search with precise token control\nExample: Find conceptually related content, not just keyword matches\nBenefit: 90% context reduction (500K → 5K tokens)\n\n{\n  \"query\": \"authentication implementation\",\n  \"max_tokens\": 6000,\n  \"search_mode\": \"hybrid\"\n}\n\nSearch modes by plan:\n\nkeyword - Fast term matching ✅ FREE\nsemantic - Embedding similarity 🔥 PRO+\nhybrid - Best of both worlds 🔥 PRO+"
      },
      {
        "title": "🌐 Multi-Repo Search",
        "body": "Plan Required: 👥 TEAM ($49/mo) or ENTERPRISE\n\nTool: rlm_multi_project_query\nUse when: You have 5+ repos and don't know which has the answer\nExample: One query searches ALL your team's projects\nTime saved: 5 minutes of manual searching → 3 seconds\n\n{\n  \"query\": \"Where do we send email notifications?\",\n  \"project_ids\": [],\n  \"max_tokens\": 8000\n}\n\n⚠️ Not available on Free/Pro plans - Requires Team plan for multi-project access."
      },
      {
        "title": "🧠 AI Memory (Remember Preferences)",
        "body": "Plan Required: 🔥 PRO ($39/mo Agents) or 👥 TEAM ($79/mo Agents)\n\nTools: rlm_remember + rlm_recall\nUse when: You want AI to remember your coding style/decisions\nBenefit: Consistent code across sessions\n\nStore a memory:\n\n{\n  \"content\": \"User prefers TypeScript strict mode with functional components\",\n  \"type\": \"preference\",\n  \"scope\": \"project\"\n}\n\nRecall later:\n\n{\n  \"query\": \"What are my coding preferences?\",\n  \"limit\": 5\n}\n\nMemory types: fact, decision, learning, preference, todo, context\n\n⚠️ Requires separate Agents plan - Memory is part of Agents features, not Context plans."
      },
      {
        "title": "👥 Team Standards (Auto-Enforce Rules)",
        "body": "Plan Required: 👥 TEAM ($49/mo) or ENTERPRISE\n\nTool: rlm_shared_context\nUse when: Your team needs consistent coding practices\nSetup once: Upload coding standards to Shared Collection\nEvery dev gets: Auto-injected team rules in every query\n\n{\n  \"categories\": [\"MANDATORY\", \"BEST_PRACTICES\"],\n  \"max_tokens\": 4000\n}\n\nCategories by priority:\n\nMANDATORY - Non-negotiable rules (security, architecture)\nBEST_PRACTICES - Recommended patterns (40% token budget)\nGUIDELINES - Helpful suggestions\nREFERENCE - Background info\n\n⚠️ Not available on Free/Pro plans - Team-wide features require Team plan."
      },
      {
        "title": "🔧 Power User Tools",
        "body": "Multi-Query (Parallel Searches):\n\n{\n  \"queries\": [\n    { \"query\": \"auth flow\", \"max_tokens\": 3000 },\n    { \"query\": \"session management\", \"max_tokens\": 3000 }\n  ]\n}\n\nDecompose (Break Down Complex Questions):\n\n{ \"query\": \"Explain the complete payment system architecture\" }\n\nPlan (Preview Execution):\n\n{ \"query\": \"Find all API endpoints\", \"strategy\": \"relevance_first\" }\n\nSearch (Regex Pattern Matching):\n\n{ \"pattern\": \"async def|async function\", \"max_results\": 20 }\n\nSession Context (Inject Standards):\n\n{ \"context\": \"Use Python 3.11+, prefer dataclasses over Pydantic\" }"
      },
      {
        "title": "📄 Document Management",
        "body": "Upload Single Doc:\n\n{ \"path\": \"docs/api.md\", \"content\": \"# API Documentation...\" }\n\nBulk Sync (CI/CD Integration):\n\n{\n  \"documents\": [\n    { \"path\": \"docs/auth.md\", \"content\": \"...\" },\n    { \"path\": \"docs/api.md\", \"content\": \"...\" }\n  ],\n  \"delete_missing\": false\n}\n\nCheck Stats:\n\n{}"
      },
      {
        "title": "Scenario 1: Solo Developer (Large Codebase)",
        "body": "Current pain: Grep/find searches take 20+ seconds, read 50K tokens per query\n\nMetricBefore SniparaWith SniparaSavingsQuery speed20 seconds2 seconds18 secondsDaily queries5050-Time per day16 minutes1.6 minutes14.4 min/dayTime per month7.2 hours0.72 hours6.5 hours/monthCost$0$0-19/moROI: 6.5 hours saved\n\nPlan recommendation: Start with FREE (100 queries), upgrade to PRO ($19/mo) if you need semantic search."
      },
      {
        "title": "Scenario 2: Team (5+ Repositories)",
        "body": "Current pain: Switch between 5 projects manually, 5 minutes per search\n\nMetricBefore SniparaWith SniparaSavingsMulti-repo search5 min3 seconds4.97 minSearches per day1010-Time per day50 minutes30 seconds49.5 min/dayTime per month24.75 hours0.25 hours24.5 hours/monthCost$0$49/mo TeamROI: 24.5 hours saved\n\nPlan recommendation: TEAM ($49/mo) for rlm_multi_project_query + shared standards."
      },
      {
        "title": "Scenario 3: Enterprise (Consistent Standards)",
        "body": "Current pain: 10 devs ask \"how do we do X?\" daily, inconsistent code\n\nBeforeWith Snipara Shared Context❌ Each dev googles/asks Slack✅ Standards auto-injected in every query❌ Inconsistent patterns✅ Enforced team conventions❌ Onboarding takes 2 weeks✅ New devs get standards instantly❌ Code review conflicts✅ Code follows standards from day 1\n\nCost: $49/mo Team or $499/mo Enterprise\nROI: Consistency + faster onboarding = easily 20+ hours/month saved"
      },
      {
        "title": "Use Case 1: \"I have huge docs and grep is slow\"",
        "body": "Plan: ✅ FREE (100 queries/mo)\n\n# 1. Index your docs once\nVisit https://snipara.com/dashboard → Create project → Upload .md/.txt files\n\n# 2. Query instantly\nrlm_ask(\"How does authentication work?\")"
      },
      {
        "title": "Use Case 2: \"I work on 10 microservices\"",
        "body": "Plan: 👥 TEAM ($49/mo)\n\n# 1. Create 10 projects on Snipara dashboard\n# 2. Enable Team plan\n\n# 3. Query all repos at once\nrlm_multi_project_query(\"How do we handle rate limiting?\")\n\n⚠️ Requires Team plan - Multi-project search not available on Free/Pro."
      },
      {
        "title": "Use Case 3: \"AI keeps forgetting my preferences\"",
        "body": "Plan: 🔥 PRO Agents ($39/mo) or 👥 TEAM Agents ($79/mo)\n\n# 1. Enable Agents plan (separate from Context plan)\n\n# 2. Store your preferences once\nrlm_remember(type=\"preference\", content=\"Use functional React components\")\n\n# 3. AI recalls them forever\nrlm_recall(\"my coding preferences\")\n\n⚠️ Requires separate Agents subscription - Memory features not included in Context plans."
      },
      {
        "title": "Context Plans (Documentation Search)",
        "body": "PlanPriceQueries/moSearch ModeMulti-ProjectFREE$0100Keyword only❌PRO$19/mo5,000Semantic + Hybrid❌TEAM$49/mo20,000Semantic + Hybrid✅ENTERPRISE$499/moUnlimitedSemantic + Hybrid✅"
      },
      {
        "title": "Agents Plans (Memory & Swarms)",
        "body": "PlanPricePrerequisiteFeaturesSTARTER$15/moNoneBasic memory (100 memories)PRO$39/moNoneUnlimited memories, swarmsTEAM$79/moContext TEAM+Team-wide memory sharingENTERPRISE$199/moContext ENTERPRISEAdvanced coordination\n\n⚠️ Two separate subscriptions: Context plans for search, Agents plans for memory/swarms.\n\nTry free first: 100 queries is ~5 days of usage to test value."
      },
      {
        "title": "Example 1: Quick Answer (FREE plan)",
        "body": "User: \"What are our API rate limits?\"\n\nYou call: rlm_ask(\"API rate limits\")\n\nResult: Returns relevant docs in 2 seconds"
      },
      {
        "title": "Example 2: Semantic Search (PRO plan)",
        "body": "User: \"How do we validate user input?\"\n\nYou call: rlm_context_query(\"user input validation\", search_mode=\"semantic\")\n\nResult: Finds docs about \"sanitization\", \"XSS prevention\", \"schema validation\"\n        even if they don't contain exact keywords"
      },
      {
        "title": "Example 3: Multi-Repo Search (TEAM plan)",
        "body": "User: \"Show me all webhook implementations across our projects\"\n\nYou call: rlm_multi_project_query(\"webhook implementation\")\n\nResult: Returns implementations from all 10 microservices in 3 seconds"
      },
      {
        "title": "Example 4: Persistent Memory (PRO Agents plan)",
        "body": "Session 1 (Monday):\n  User: \"I prefer TypeScript strict mode and functional components\"\n  You call: rlm_remember(type=\"preference\", content=\"Prefers TS strict + functional\")\n\nSession 2 (Friday - NEW SESSION):\n  User: \"Create a new React component\"\n  You call: rlm_recall(\"coding preferences\")\n  Result: AI remembers to use functional components from Monday!"
      },
      {
        "title": "Example 5: Team Standards (TEAM plan)",
        "body": "Setup (Admin does once):\n  - Upload coding standards to Shared Context Collection\n  - Link collection to all team projects\n\nEvery developer:\n  User: \"Write a new API endpoint\"\n  You call: rlm_shared_context(categories=[\"MANDATORY\"])\n  Result: Auto-injects team's API design rules, security requirements, etc."
      },
      {
        "title": "Support & Resources",
        "body": "Website: https://snipara.com\nDocumentation: https://docs.snipara.com\nGitHub: https://github.com/snipara/snipara-mcp\nIssues: https://github.com/snipara/snipara-mcp/issues\nEmail: support@snipara.com"
      },
      {
        "title": "Quick Tips",
        "body": "Start small: Use rlm_ask for quick answers on FREE plan\nUpgrade smart: Get PRO when keyword search isn't finding what you need\nTeam value: Multi-project search pays for itself with 5+ repos\nMemory requires separate plan: Context + Agents are two subscriptions\nIndex first: Upload docs to dashboard before querying\n\nWhen in doubt, start with FREE and upgrade based on value received. 🚀"
      },
      {
        "title": "Query Tools (All Plans)",
        "body": "rlm_ask - Quick keyword search\n\n{ \"query\": \"API rate limits\" }\n\nrlm_context_query - Full-featured semantic search\n\n{\n  \"query\": \"authentication\",\n  \"max_tokens\": 6000,\n  \"search_mode\": \"hybrid\",\n  \"include_metadata\": true\n}\n\nrlm_search - Regex pattern search\n\n{\n  \"pattern\": \"async def|async function\",\n  \"max_results\": 20\n}\n\nrlm_inject - Set session context\n\n{\n  \"context\": \"Use Python 3.11+, prefer dataclasses\",\n  \"append\": false\n}\n\nrlm_context - Show current session context\n\n{}\n\nrlm_clear_context - Clear session context\n\n{}"
      },
      {
        "title": "Advanced Query Tools (Pro+)",
        "body": "rlm_multi_query - Parallel queries\n\n{\n  \"queries\": [\n    { \"query\": \"auth flow\", \"max_tokens\": 3000 },\n    { \"query\": \"session management\", \"max_tokens\": 3000 }\n  ],\n  \"max_tokens\": 8000\n}\n\nrlm_decompose - Break down complex questions\n\n{\n  \"query\": \"Explain payment system architecture\",\n  \"max_depth\": 2\n}\n\nrlm_plan - Generate execution plan\n\n{\n  \"query\": \"Find all API endpoints\",\n  \"strategy\": \"relevance_first\",\n  \"max_tokens\": 16000\n}"
      },
      {
        "title": "Team Tools (Team+ Plan)",
        "body": "rlm_multi_project_query - Search across all repos\n\n{\n  \"query\": \"webhook implementation\",\n  \"project_ids\": [],\n  \"exclude_project_ids\": [],\n  \"max_tokens\": 8000,\n  \"per_project_limit\": 3\n}\n\nrlm_shared_context - Get team standards\n\n{\n  \"categories\": [\"MANDATORY\", \"BEST_PRACTICES\"],\n  \"max_tokens\": 4000,\n  \"include_content\": true\n}\n\nrlm_list_templates - Browse prompt templates\n\n{\n  \"category\": \"code-review\"\n}\n\nrlm_get_template - Use template with variables\n\n{\n  \"slug\": \"security-review\",\n  \"variables\": {\n    \"author\": \"John\",\n    \"pr_number\": \"123\"\n  }\n}\n\nrlm_list_collections - List shared collections\n\n{\n  \"include_public\": true\n}\n\nrlm_upload_shared_document - Upload to shared collection\n\n{\n  \"collection_id\": \"col_abc123\",\n  \"title\": \"TypeScript Standards\",\n  \"content\": \"# Standards...\",\n  \"category\": \"BEST_PRACTICES\",\n  \"priority\": 90\n}"
      },
      {
        "title": "Memory Tools (Agents Plan)",
        "body": "rlm_remember - Store memory\n\n{\n  \"content\": \"User prefers functional components\",\n  \"type\": \"preference\",\n  \"scope\": \"project\",\n  \"category\": \"coding-style\",\n  \"ttl_days\": null\n}\n\nrlm_recall - Query memories\n\n{\n  \"query\": \"What are my preferences?\",\n  \"type\": \"preference\",\n  \"limit\": 5,\n  \"min_relevance\": 0.5\n}\n\nrlm_memories - List all memories\n\n{\n  \"type\": \"preference\",\n  \"category\": \"coding-style\",\n  \"limit\": 20,\n  \"offset\": 0\n}\n\nrlm_forget - Delete memories\n\n{\n  \"memory_id\": \"mem_abc123\"\n}"
      },
      {
        "title": "Document Management Tools",
        "body": "rlm_upload_document - Upload single doc\n\n{\n  \"path\": \"docs/api.md\",\n  \"content\": \"# API Documentation...\"\n}\n\nrlm_sync_documents - Bulk upload\n\n{\n  \"documents\": [\n    { \"path\": \"docs/auth.md\", \"content\": \"...\" },\n    { \"path\": \"docs/api.md\", \"content\": \"...\" }\n  ],\n  \"delete_missing\": false\n}\n\nrlm_store_summary - Store document summary\n\n{\n  \"document_path\": \"docs/api.md\",\n  \"summary\": \"RESTful API with OAuth2 auth...\",\n  \"summary_type\": \"concise\",\n  \"generated_by\": \"claude-3.5-sonnet\"\n}\n\nrlm_get_summaries - Get stored summaries\n\n{\n  \"document_path\": \"docs/api.md\",\n  \"summary_type\": \"concise\"\n}\n\nrlm_stats - Get documentation stats\n\n{}\n\nrlm_sections - List indexed sections\n\n{\n  \"filter\": \"auth\",\n  \"limit\": 50,\n  \"offset\": 0\n}\n\nrlm_read - Read specific lines\n\n{\n  \"start_line\": 1,\n  \"end_line\": 100\n}"
      },
      {
        "title": "Advanced Features (Enterprise)",
        "body": "rlm_swarm_create - Create agent swarm\n\n{\n  \"name\": \"code-review-swarm\",\n  \"description\": \"Parallel code review\",\n  \"max_agents\": 10\n}\n\nrlm_swarm_join - Join swarm\n\n{\n  \"swarm_id\": \"swarm_abc123\",\n  \"agent_id\": \"agent_1\",\n  \"role\": \"worker\",\n  \"capabilities\": [\"review\", \"test\"]\n}\n\nrlm_claim - Claim resource for exclusive access\n\n{\n  \"swarm_id\": \"swarm_abc123\",\n  \"agent_id\": \"agent_1\",\n  \"resource_type\": \"file\",\n  \"resource_id\": \"src/auth.ts\",\n  \"timeout_seconds\": 300\n}\n\nrlm_release - Release claimed resource\n\n{\n  \"swarm_id\": \"swarm_abc123\",\n  \"agent_id\": \"agent_1\",\n  \"claim_id\": \"claim_abc123\"\n}\n\nrlm_state_get - Read swarm state\n\n{\n  \"swarm_id\": \"swarm_abc123\",\n  \"key\": \"progress\"\n}\n\nrlm_state_set - Write swarm state\n\n{\n  \"swarm_id\": \"swarm_abc123\",\n  \"agent_id\": \"agent_1\",\n  \"key\": \"progress\",\n  \"value\": { \"completed\": 5, \"total\": 10 },\n  \"expected_version\": 1\n}\n\nrlm_broadcast - Broadcast event to swarm\n\n{\n  \"swarm_id\": \"swarm_abc123\",\n  \"agent_id\": \"agent_1\",\n  \"event_type\": \"task_completed\",\n  \"payload\": { \"task_id\": \"task_1\" }\n}\n\nrlm_task_create - Create swarm task\n\n{\n  \"swarm_id\": \"swarm_abc123\",\n  \"agent_id\": \"agent_1\",\n  \"title\": \"Review auth module\",\n  \"description\": \"Security review\",\n  \"priority\": 90\n}\n\nrlm_task_claim - Claim task from queue\n\n{\n  \"swarm_id\": \"swarm_abc123\",\n  \"agent_id\": \"agent_1\",\n  \"task_id\": \"task_abc123\"\n}\n\nrlm_task_complete - Mark task complete\n\n{\n  \"swarm_id\": \"swarm_abc123\",\n  \"agent_id\": \"agent_1\",\n  \"task_id\": \"task_abc123\",\n  \"success\": true,\n  \"result\": { \"issues_found\": 0 }\n}"
      },
      {
        "title": "Settings & Configuration",
        "body": "rlm_settings - Get project settings\n\n{\n  \"refresh\": false\n}\n\nReturns current project configuration including:\n\nMax tokens per query\nDefault search mode\nRate limits\nEnabled features\n\nFor complete API documentation, visit: https://docs.snipara.com"
      }
    ],
    "body": "name: Snipara MCP - Smart Documentation Search description: Find answers in your codebase 10x faster with semantic search. Query multiple repos at once. AI remembers your preferences across sessions.\n\nSystem Instructions for AI Agents\n\nYou are an AI assistant with access to Snipara MCP tools. Use these tools to provide faster, more accurate answers by querying pre-indexed documentation instead of reading files one-by-one.\n\nWhen to Use Snipara Tools\n\n✅ USE Snipara when:\n\nUser asks \"How does X work?\" → Use rlm_ask or rlm_context_query\nUser asks \"Where do we do X?\" → Use rlm_multi_project_query (if Team plan)\nUser asks \"What are my preferences?\" → Use rlm_recall\nYou need to find code patterns across multiple repos\nYou need to understand architecture/documentation\n\n❌ DON'T use Snipara when:\n\nUser asks you to read a SPECIFIC file they named → Use native Read tool\nUser asks you to edit/write code → Use native Edit/Write tools\nUser asks to run commands → Use native Bash tool\nSnipara API returns error → Fall back to native tools\nRecommended Workflow\nFirst query: Always start with rlm_ask (fast, works on Free plan)\nIf not found: Try rlm_context_query with search_mode: \"semantic\" (requires Pro)\nMulti-repo search: Use rlm_multi_project_query if user has Team plan\nRemember decisions: Use rlm_remember to store important info for future sessions\nError Handling\n\nIf Snipara returns an error:\n\nCheck if user has required plan (Free/Pro/Team)\nCheck if docs are indexed (user needs to upload to dashboard first)\nFall back to native Read/Grep/Glob tools\nExplain to user what went wrong and suggest solution\nExample Usage\nUser: \"How does our authentication system work?\"\n\nGood response:\n1. Call rlm_ask(\"authentication system\")\n2. Get relevant docs in 2 seconds\n3. Synthesize answer from returned context\n\nBad response:\n1. Use Grep to search for \"auth\"\n2. Read 10 files sequentially\n3. Hit token limits\n4. Give incomplete answer\n\nGet Started in 2 Minutes\nThe Problem You Have Right Now\n\nYour AI assistant searches files one-by-one using grep/find. With large codebases:\n\n❌ Queries take 20+ seconds\n❌ AI reads 50K tokens to answer simple questions\n❌ You manually search 5 repos to find \"how we do X\"\n❌ AI forgets your preferences next session\nThe Solution (30 seconds from now)\n# 1. Install\npip install snipara-mcp   # Python\nnpm install snipara-mcp   # Node.js\n\n# 2. Get your API key\n# Sign up at https://snipara.com (Free: 100 queries/month)\n\n# 3. Set environment variable\nexport SNIPARA_API_KEY=\"your-key-here\"\n\n# 4. Add to your MCP client (Claude Code, Cline, Roo Code, etc.)\n# Done! Start using rlm_ask() in your next chat\n\nYour First Query (Try This Now)\nYou: \"How does authentication work in my codebase?\"\n\nBehind the scenes:\n  rlm_context_query(\"authentication\")\n  → 2 seconds later\n  → Returns top 3 relevant docs (3K tokens instead of 50K)\n\nResult: Instant, accurate answer\n\n\nNote: Before querying, index your docs at https://snipara.com/dashboard (upload .md/.txt/.mdx files).\n\nCore Capabilities (Pick What You Need)\n🎯 Quick Answers (Start Here)\n\nPlan Required: ✅ FREE (100 queries/mo)\n\nTool: rlm_ask Use when: You need a fast answer from your docs Example: rlm_ask(\"API rate limits\") Time saved: 20 seconds → 2 seconds per query\n\n{ \"query\": \"How do we handle webhooks?\" }\n\n🔍 Deep Research (Complex Questions)\n\nPlan Required: ✅ FREE (keyword only) | 🔥 PRO ($19/mo for semantic)\n\nTool: rlm_context_query Use when: You need semantic search with precise token control Example: Find conceptually related content, not just keyword matches Benefit: 90% context reduction (500K → 5K tokens)\n\n{\n  \"query\": \"authentication implementation\",\n  \"max_tokens\": 6000,\n  \"search_mode\": \"hybrid\"\n}\n\n\nSearch modes by plan:\n\nkeyword - Fast term matching ✅ FREE\nsemantic - Embedding similarity 🔥 PRO+\nhybrid - Best of both worlds 🔥 PRO+\n🌐 Multi-Repo Search\n\nPlan Required: 👥 TEAM ($49/mo) or ENTERPRISE\n\nTool: rlm_multi_project_query Use when: You have 5+ repos and don't know which has the answer Example: One query searches ALL your team's projects Time saved: 5 minutes of manual searching → 3 seconds\n\n{\n  \"query\": \"Where do we send email notifications?\",\n  \"project_ids\": [],\n  \"max_tokens\": 8000\n}\n\n\n⚠️ Not available on Free/Pro plans - Requires Team plan for multi-project access.\n\n🧠 AI Memory (Remember Preferences)\n\nPlan Required: 🔥 PRO ($39/mo Agents) or 👥 TEAM ($79/mo Agents)\n\nTools: rlm_remember + rlm_recall Use when: You want AI to remember your coding style/decisions Benefit: Consistent code across sessions\n\nStore a memory:\n\n{\n  \"content\": \"User prefers TypeScript strict mode with functional components\",\n  \"type\": \"preference\",\n  \"scope\": \"project\"\n}\n\n\nRecall later:\n\n{\n  \"query\": \"What are my coding preferences?\",\n  \"limit\": 5\n}\n\n\nMemory types: fact, decision, learning, preference, todo, context\n\n⚠️ Requires separate Agents plan - Memory is part of Agents features, not Context plans.\n\n👥 Team Standards (Auto-Enforce Rules)\n\nPlan Required: 👥 TEAM ($49/mo) or ENTERPRISE\n\nTool: rlm_shared_context Use when: Your team needs consistent coding practices Setup once: Upload coding standards to Shared Collection Every dev gets: Auto-injected team rules in every query\n\n{\n  \"categories\": [\"MANDATORY\", \"BEST_PRACTICES\"],\n  \"max_tokens\": 4000\n}\n\n\nCategories by priority:\n\nMANDATORY - Non-negotiable rules (security, architecture)\nBEST_PRACTICES - Recommended patterns (40% token budget)\nGUIDELINES - Helpful suggestions\nREFERENCE - Background info\n\n⚠️ Not available on Free/Pro plans - Team-wide features require Team plan.\n\n🔧 Power User Tools\n\nMulti-Query (Parallel Searches):\n\n{\n  \"queries\": [\n    { \"query\": \"auth flow\", \"max_tokens\": 3000 },\n    { \"query\": \"session management\", \"max_tokens\": 3000 }\n  ]\n}\n\n\nDecompose (Break Down Complex Questions):\n\n{ \"query\": \"Explain the complete payment system architecture\" }\n\n\nPlan (Preview Execution):\n\n{ \"query\": \"Find all API endpoints\", \"strategy\": \"relevance_first\" }\n\n\nSearch (Regex Pattern Matching):\n\n{ \"pattern\": \"async def|async function\", \"max_results\": 20 }\n\n\nSession Context (Inject Standards):\n\n{ \"context\": \"Use Python 3.11+, prefer dataclasses over Pydantic\" }\n\n📄 Document Management\n\nUpload Single Doc:\n\n{ \"path\": \"docs/api.md\", \"content\": \"# API Documentation...\" }\n\n\nBulk Sync (CI/CD Integration):\n\n{\n  \"documents\": [\n    { \"path\": \"docs/auth.md\", \"content\": \"...\" },\n    { \"path\": \"docs/api.md\", \"content\": \"...\" }\n  ],\n  \"delete_missing\": false\n}\n\n\nCheck Stats:\n\n{}\n\nROI Calculator\nScenario 1: Solo Developer (Large Codebase)\n\nCurrent pain: Grep/find searches take 20+ seconds, read 50K tokens per query\n\nMetric\tBefore Snipara\tWith Snipara\tSavings\nQuery speed\t20 seconds\t2 seconds\t18 seconds\nDaily queries\t50\t50\t-\nTime per day\t16 minutes\t1.6 minutes\t14.4 min/day\nTime per month\t7.2 hours\t0.72 hours\t6.5 hours/month\nCost\t$0\t$0-19/mo\tROI: 6.5 hours saved\n\nPlan recommendation: Start with FREE (100 queries), upgrade to PRO ($19/mo) if you need semantic search.\n\nScenario 2: Team (5+ Repositories)\n\nCurrent pain: Switch between 5 projects manually, 5 minutes per search\n\nMetric\tBefore Snipara\tWith Snipara\tSavings\nMulti-repo search\t5 min\t3 seconds\t4.97 min\nSearches per day\t10\t10\t-\nTime per day\t50 minutes\t30 seconds\t49.5 min/day\nTime per month\t24.75 hours\t0.25 hours\t24.5 hours/month\nCost\t$0\t$49/mo Team\tROI: 24.5 hours saved\n\nPlan recommendation: TEAM ($49/mo) for rlm_multi_project_query + shared standards.\n\nScenario 3: Enterprise (Consistent Standards)\n\nCurrent pain: 10 devs ask \"how do we do X?\" daily, inconsistent code\n\nBefore\tWith Snipara Shared Context\n❌ Each dev googles/asks Slack\t✅ Standards auto-injected in every query\n❌ Inconsistent patterns\t✅ Enforced team conventions\n❌ Onboarding takes 2 weeks\t✅ New devs get standards instantly\n❌ Code review conflicts\t✅ Code follows standards from day 1\n\nCost: $49/mo Team or $499/mo Enterprise ROI: Consistency + faster onboarding = easily 20+ hours/month saved\n\nQuick Start by Use Case\nUse Case 1: \"I have huge docs and grep is slow\"\n\nPlan: ✅ FREE (100 queries/mo)\n\n# 1. Index your docs once\nVisit https://snipara.com/dashboard → Create project → Upload .md/.txt files\n\n# 2. Query instantly\nrlm_ask(\"How does authentication work?\")\n\nUse Case 2: \"I work on 10 microservices\"\n\nPlan: 👥 TEAM ($49/mo)\n\n# 1. Create 10 projects on Snipara dashboard\n# 2. Enable Team plan\n\n# 3. Query all repos at once\nrlm_multi_project_query(\"How do we handle rate limiting?\")\n\n\n⚠️ Requires Team plan - Multi-project search not available on Free/Pro.\n\nUse Case 3: \"AI keeps forgetting my preferences\"\n\nPlan: 🔥 PRO Agents ($39/mo) or 👥 TEAM Agents ($79/mo)\n\n# 1. Enable Agents plan (separate from Context plan)\n\n# 2. Store your preferences once\nrlm_remember(type=\"preference\", content=\"Use functional React components\")\n\n# 3. AI recalls them forever\nrlm_recall(\"my coding preferences\")\n\n\n⚠️ Requires separate Agents subscription - Memory features not included in Context plans.\n\nPricing (Two Subscription Types)\nContext Plans (Documentation Search)\nPlan\tPrice\tQueries/mo\tSearch Mode\tMulti-Project\nFREE\t$0\t100\tKeyword only\t❌\nPRO\t$19/mo\t5,000\tSemantic + Hybrid\t❌\nTEAM\t$49/mo\t20,000\tSemantic + Hybrid\t✅\nENTERPRISE\t$499/mo\tUnlimited\tSemantic + Hybrid\t✅\nAgents Plans (Memory & Swarms)\nPlan\tPrice\tPrerequisite\tFeatures\nSTARTER\t$15/mo\tNone\tBasic memory (100 memories)\nPRO\t$39/mo\tNone\tUnlimited memories, swarms\nTEAM\t$79/mo\tContext TEAM+\tTeam-wide memory sharing\nENTERPRISE\t$199/mo\tContext ENTERPRISE\tAdvanced coordination\n\n⚠️ Two separate subscriptions: Context plans for search, Agents plans for memory/swarms.\n\nTry free first: 100 queries is ~5 days of usage to test value.\n\nExample Workflows\nExample 1: Quick Answer (FREE plan)\nUser: \"What are our API rate limits?\"\n\nYou call: rlm_ask(\"API rate limits\")\n\nResult: Returns relevant docs in 2 seconds\n\nExample 2: Semantic Search (PRO plan)\nUser: \"How do we validate user input?\"\n\nYou call: rlm_context_query(\"user input validation\", search_mode=\"semantic\")\n\nResult: Finds docs about \"sanitization\", \"XSS prevention\", \"schema validation\"\n        even if they don't contain exact keywords\n\nExample 3: Multi-Repo Search (TEAM plan)\nUser: \"Show me all webhook implementations across our projects\"\n\nYou call: rlm_multi_project_query(\"webhook implementation\")\n\nResult: Returns implementations from all 10 microservices in 3 seconds\n\nExample 4: Persistent Memory (PRO Agents plan)\nSession 1 (Monday):\n  User: \"I prefer TypeScript strict mode and functional components\"\n  You call: rlm_remember(type=\"preference\", content=\"Prefers TS strict + functional\")\n\nSession 2 (Friday - NEW SESSION):\n  User: \"Create a new React component\"\n  You call: rlm_recall(\"coding preferences\")\n  Result: AI remembers to use functional components from Monday!\n\nExample 5: Team Standards (TEAM plan)\nSetup (Admin does once):\n  - Upload coding standards to Shared Context Collection\n  - Link collection to all team projects\n\nEvery developer:\n  User: \"Write a new API endpoint\"\n  You call: rlm_shared_context(categories=[\"MANDATORY\"])\n  Result: Auto-injects team's API design rules, security requirements, etc.\n\nSupport & Resources\nWebsite: https://snipara.com\nDocumentation: https://docs.snipara.com\nGitHub: https://github.com/snipara/snipara-mcp\nIssues: https://github.com/snipara/snipara-mcp/issues\nEmail: support@snipara.com\nQuick Tips\nStart small: Use rlm_ask for quick answers on FREE plan\nUpgrade smart: Get PRO when keyword search isn't finding what you need\nTeam value: Multi-project search pays for itself with 5+ repos\nMemory requires separate plan: Context + Agents are two subscriptions\nIndex first: Upload docs to dashboard before querying\n\nWhen in doubt, start with FREE and upgrade based on value received. 🚀\n\nComplete Tool Reference (For Power Users)\nQuery Tools (All Plans)\n\nrlm_ask - Quick keyword search\n\n{ \"query\": \"API rate limits\" }\n\n\nrlm_context_query - Full-featured semantic search\n\n{\n  \"query\": \"authentication\",\n  \"max_tokens\": 6000,\n  \"search_mode\": \"hybrid\",\n  \"include_metadata\": true\n}\n\n\nrlm_search - Regex pattern search\n\n{\n  \"pattern\": \"async def|async function\",\n  \"max_results\": 20\n}\n\n\nrlm_inject - Set session context\n\n{\n  \"context\": \"Use Python 3.11+, prefer dataclasses\",\n  \"append\": false\n}\n\n\nrlm_context - Show current session context\n\n{}\n\n\nrlm_clear_context - Clear session context\n\n{}\n\nAdvanced Query Tools (Pro+)\n\nrlm_multi_query - Parallel queries\n\n{\n  \"queries\": [\n    { \"query\": \"auth flow\", \"max_tokens\": 3000 },\n    { \"query\": \"session management\", \"max_tokens\": 3000 }\n  ],\n  \"max_tokens\": 8000\n}\n\n\nrlm_decompose - Break down complex questions\n\n{\n  \"query\": \"Explain payment system architecture\",\n  \"max_depth\": 2\n}\n\n\nrlm_plan - Generate execution plan\n\n{\n  \"query\": \"Find all API endpoints\",\n  \"strategy\": \"relevance_first\",\n  \"max_tokens\": 16000\n}\n\nTeam Tools (Team+ Plan)\n\nrlm_multi_project_query - Search across all repos\n\n{\n  \"query\": \"webhook implementation\",\n  \"project_ids\": [],\n  \"exclude_project_ids\": [],\n  \"max_tokens\": 8000,\n  \"per_project_limit\": 3\n}\n\n\nrlm_shared_context - Get team standards\n\n{\n  \"categories\": [\"MANDATORY\", \"BEST_PRACTICES\"],\n  \"max_tokens\": 4000,\n  \"include_content\": true\n}\n\n\nrlm_list_templates - Browse prompt templates\n\n{\n  \"category\": \"code-review\"\n}\n\n\nrlm_get_template - Use template with variables\n\n{\n  \"slug\": \"security-review\",\n  \"variables\": {\n    \"author\": \"John\",\n    \"pr_number\": \"123\"\n  }\n}\n\n\nrlm_list_collections - List shared collections\n\n{\n  \"include_public\": true\n}\n\n\nrlm_upload_shared_document - Upload to shared collection\n\n{\n  \"collection_id\": \"col_abc123\",\n  \"title\": \"TypeScript Standards\",\n  \"content\": \"# Standards...\",\n  \"category\": \"BEST_PRACTICES\",\n  \"priority\": 90\n}\n\nMemory Tools (Agents Plan)\n\nrlm_remember - Store memory\n\n{\n  \"content\": \"User prefers functional components\",\n  \"type\": \"preference\",\n  \"scope\": \"project\",\n  \"category\": \"coding-style\",\n  \"ttl_days\": null\n}\n\n\nrlm_recall - Query memories\n\n{\n  \"query\": \"What are my preferences?\",\n  \"type\": \"preference\",\n  \"limit\": 5,\n  \"min_relevance\": 0.5\n}\n\n\nrlm_memories - List all memories\n\n{\n  \"type\": \"preference\",\n  \"category\": \"coding-style\",\n  \"limit\": 20,\n  \"offset\": 0\n}\n\n\nrlm_forget - Delete memories\n\n{\n  \"memory_id\": \"mem_abc123\"\n}\n\nDocument Management Tools\n\nrlm_upload_document - Upload single doc\n\n{\n  \"path\": \"docs/api.md\",\n  \"content\": \"# API Documentation...\"\n}\n\n\nrlm_sync_documents - Bulk upload\n\n{\n  \"documents\": [\n    { \"path\": \"docs/auth.md\", \"content\": \"...\" },\n    { \"path\": \"docs/api.md\", \"content\": \"...\" }\n  ],\n  \"delete_missing\": false\n}\n\n\nrlm_store_summary - Store document summary\n\n{\n  \"document_path\": \"docs/api.md\",\n  \"summary\": \"RESTful API with OAuth2 auth...\",\n  \"summary_type\": \"concise\",\n  \"generated_by\": \"claude-3.5-sonnet\"\n}\n\n\nrlm_get_summaries - Get stored summaries\n\n{\n  \"document_path\": \"docs/api.md\",\n  \"summary_type\": \"concise\"\n}\n\n\nrlm_stats - Get documentation stats\n\n{}\n\n\nrlm_sections - List indexed sections\n\n{\n  \"filter\": \"auth\",\n  \"limit\": 50,\n  \"offset\": 0\n}\n\n\nrlm_read - Read specific lines\n\n{\n  \"start_line\": 1,\n  \"end_line\": 100\n}\n\nAdvanced Features (Enterprise)\n\nrlm_swarm_create - Create agent swarm\n\n{\n  \"name\": \"code-review-swarm\",\n  \"description\": \"Parallel code review\",\n  \"max_agents\": 10\n}\n\n\nrlm_swarm_join - Join swarm\n\n{\n  \"swarm_id\": \"swarm_abc123\",\n  \"agent_id\": \"agent_1\",\n  \"role\": \"worker\",\n  \"capabilities\": [\"review\", \"test\"]\n}\n\n\nrlm_claim - Claim resource for exclusive access\n\n{\n  \"swarm_id\": \"swarm_abc123\",\n  \"agent_id\": \"agent_1\",\n  \"resource_type\": \"file\",\n  \"resource_id\": \"src/auth.ts\",\n  \"timeout_seconds\": 300\n}\n\n\nrlm_release - Release claimed resource\n\n{\n  \"swarm_id\": \"swarm_abc123\",\n  \"agent_id\": \"agent_1\",\n  \"claim_id\": \"claim_abc123\"\n}\n\n\nrlm_state_get - Read swarm state\n\n{\n  \"swarm_id\": \"swarm_abc123\",\n  \"key\": \"progress\"\n}\n\n\nrlm_state_set - Write swarm state\n\n{\n  \"swarm_id\": \"swarm_abc123\",\n  \"agent_id\": \"agent_1\",\n  \"key\": \"progress\",\n  \"value\": { \"completed\": 5, \"total\": 10 },\n  \"expected_version\": 1\n}\n\n\nrlm_broadcast - Broadcast event to swarm\n\n{\n  \"swarm_id\": \"swarm_abc123\",\n  \"agent_id\": \"agent_1\",\n  \"event_type\": \"task_completed\",\n  \"payload\": { \"task_id\": \"task_1\" }\n}\n\n\nrlm_task_create - Create swarm task\n\n{\n  \"swarm_id\": \"swarm_abc123\",\n  \"agent_id\": \"agent_1\",\n  \"title\": \"Review auth module\",\n  \"description\": \"Security review\",\n  \"priority\": 90\n}\n\n\nrlm_task_claim - Claim task from queue\n\n{\n  \"swarm_id\": \"swarm_abc123\",\n  \"agent_id\": \"agent_1\",\n  \"task_id\": \"task_abc123\"\n}\n\n\nrlm_task_complete - Mark task complete\n\n{\n  \"swarm_id\": \"swarm_abc123\",\n  \"agent_id\": \"agent_1\",\n  \"task_id\": \"task_abc123\",\n  \"success\": true,\n  \"result\": { \"issues_found\": 0 }\n}\n\nSettings & Configuration\n\nrlm_settings - Get project settings\n\n{\n  \"refresh\": false\n}\n\n\nReturns current project configuration including:\n\nMax tokens per query\nDefault search mode\nRate limits\nEnabled features\n\nFor complete API documentation, visit: https://docs.snipara.com"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/alopez3006/snipara-mcp",
    "publisherUrl": "https://clawhub.ai/alopez3006/snipara-mcp",
    "owner": "alopez3006",
    "version": "0.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/snipara-mcp",
    "downloadUrl": "https://openagent3.xyz/downloads/snipara-mcp",
    "agentUrl": "https://openagent3.xyz/skills/snipara-mcp/agent",
    "manifestUrl": "https://openagent3.xyz/skills/snipara-mcp/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/snipara-mcp/agent.md"
  }
}