Skip to main content
Glama
Claude MCP Knowledge Base
by grandinh

Claude MCP Knowledge Base

Eliminate repeated MCP research - A persistent knowledge base server for Model Context Protocol (MCP) development with GitHub integration and removal blocklist.

Features

  • Zero-Research MCP Creation: Built-in knowledge of MCP specifications, best practices, and patterns

  • Always Up-to-Date: Automatically syncs from official MCP repositories and community examples

  • GitHub Integration: Indexes your .claude/ directories across all repositories

  • Removal Blocklist: Track deleted MCPs and exclude file patterns permanently

  • Periodic Sync: Auto-updates knowledge base every 30 minutes (configurable)

  • Fast Search: Keyword-based search across all indexed documentation

Related MCP server: obsidian-kb

Quick Start

Prerequisites

  • Node.js ≥18

  • GitHub Personal Access Token (for indexing repos)

Installation

npm install -g @grandinharrison/claude-mcp-kb

Or use with npx:

npx @grandinharrison/claude-mcp-kb

Setup

  1. Set GitHub Token:

export GITHUB_TOKEN="your_github_pat_here"

Or authenticate with Claude Code (token will be auto-detected from ~/.claude/.credentials.json).

  1. Add to Claude Code:

Add to your .claude/settings.json:

{
  "mcpServers": {
    "knowledge-base": {
      "command": "npx",
      "args": ["-y", "@grandinharrison/claude-mcp-kb"],
      "env": {
        "GITHUB_TOKEN": "your_token_here"
      }
    }
  }
}

Or use the CLI:

claude mcp add --transport stdio knowledge-base -- npx @grandinharrison/claude-mcp-kb
  1. First Run:

The server will automatically:

  • Create ~/.claude-kb/ directory

  • Index official MCP repositories

  • Discover your repos with .claude/ directories

  • Start periodic sync (every 30 minutes)

Usage

Available Tools

search_knowledge_base

Search MCP documentation, examples, and best practices.

{
  "query": "how to implement MCP tool with error handling",
  "maxResults": 10
}

Returns: Ranked search results with snippets and source files.

get_mcp_specification

Get current MCP protocol spec, best practices, and common patterns.

{}

Returns: Complete MCP specification with lifecycle, transports, capabilities.

list_repositories

List all indexed repositories with file counts.

{}

Returns: Repository list with counts.

add_blocklist_entry

Add MCP server or file pattern to blocklist.

{
  "type": "file_pattern",
  "pattern": "**/*.secret.md",
  "reason": "Contains sensitive information"
}

Or block a server:

{
  "type": "server",
  "serverName": "@example/bad-mcp-server",
  "reason": "Security vulnerability"
}

check_blocklist

Check if something is blocked.

{
  "serverName": "@example/my-server"
}

update_knowledge_base

Manually trigger sync (normally automatic).

{
  "force": true
}

Configuration

Edit ~/.claude-kb/config.json:

{
  "version": "1.0.0",
  "repositories": [
    {
      "owner": "your-org",
      "repo": "your-repo",
      "branch": "main",
      "includePatterns": [".claude/**/*.md"],
      "excludePatterns": ["**/node_modules/**"],
      "indexingEnabled": true,
      "type": "user"
    }
  ],
  "sync": {
    "enabled": true,
    "intervalMinutes": 30,
    "autoDiscoverUserRepos": true,
    "includeOfficialMCPRepos": true,
    "includeCommunityRepos": true
  },
  "storage": {
    "cacheDir": "~/.claude-kb",
    "maxIndexSizeMB": 1000
  },
  "blocklist": {
    "enabled": true,
    "strict": true
  }
}

Configuration Options

  • repositories: Explicitly configured repos to index

  • sync.intervalMinutes: How often to sync (5-1440 minutes)

  • sync.autoDiscoverUserRepos: Auto-find your repos with .claude/ dirs

  • sync.includeOfficialMCPRepos: Index modelcontextprotocol/* repos

  • sync.includeCommunityRepos: Index awesome-mcp-servers lists

  • blocklist.strict: Block without prompting user

Blocklist

The blocklist is stored in ~/.claude-kb/data/blocklist.json as an append-only log.

Block a File Pattern

{
  "type": "file_pattern",
  "pattern": "**/private/**",
  "reason": "Exclude private directories"
}

Block an MCP Server

{
  "type": "server",
  "serverName": "@malicious/mcp-server",
  "version": "1.0.0",
  "reason": "Security vulnerability CVE-2025-12345"
}

Removal is Permanent

Once blocked, entries remain in the log forever (unless manually edited). To override:

  1. Edit ~/.claude-kb/data/blocklist.json

  2. Set allowOverride: true on the entry

  3. Restart server

Storage Structure

~/.claude-kb/
├── config.json              # Configuration
├── data/
│   ├── specification.json   # MCP spec cache
│   └── blocklist.json       # Blocklist log
├── repos/                   # Cached repository content
│   ├── modelcontextprotocol/
│   │   └── servers/
│   └── your-username/
│       └── your-repo/
└── templates/               # MCP templates (future)

Development

Build from Source

git clone https://github.com/grandinharrison/claude-mcp-kb.git
cd claude-mcp-kb
npm install
npm run build

Run in Dev Mode

npm run dev

Run Tests

npm test

Roadmap

Current (v0.1.0)

  • ✅ Basic keyword search

  • ✅ GitHub integration

  • ✅ Periodic sync

  • ✅ Blocklist (servers + file patterns)

  • ✅ Official MCP repos indexing

  • ✅ Auto-discover user repos

Planned (v0.2.0)

  • Vector search (txtai/FAISS integration)

  • Semantic similarity scoring

  • MCP server templates generation

  • Real-time webhook sync

  • Web UI for blocklist management

Future

  • Multi-cloud support (GitLab, Bitbucket)

  • Team collaboration features

  • Usage analytics

  • Knowledge graph relationships

Troubleshooting

"GitHub token not found"

Set GITHUB_TOKEN environment variable or authenticate with Claude Code.

"Error fetching repo"

Check:

  1. Token has repo scope

  2. Repository exists and you have access

  3. Network connectivity

Knowledge base not updating

  1. Check ~/.claude-kb/config.json - ensure sync.enabled: true

  2. Manually trigger: update_knowledge_base tool

  3. Check logs in stderr output

Slow searches

Current MVP uses keyword search. Upgrade to vector search in v0.2.0 for faster semantic search.

Contributing

Contributions welcome! Please:

  1. Fork the repository

  2. Create a feature branch

  3. Add tests for new functionality

  4. Submit a pull request

License

MIT License - see LICENSE file

Author

Harrison Grandin

Acknowledgments

Available Tools

6 tools
add_blocklist_entryA

Add an entry to the blocklist. Can block MCP servers or exclude file patterns from indexing.

Inputs: type (required), reason (required), pattern, serverName.

check_blocklistC

Check if a server or file pattern is blocked.

Inputs: pattern, serverName.

get_mcp_specificationA

Get the current MCP protocol specification, best practices, and common patterns. Always up-to-date knowledge about MCP development.

Inputs: no named parameters.

list_repositoriesA

List all repositories currently indexed in the knowledge base with file counts.

Inputs: no named parameters.

search_knowledge_baseA

Search the MCP knowledge base for documentation, examples, and best practices. Searches across official MCP repos, community servers, and your repositories with .claude/ directories.

Inputs: query (required), maxResults.

update_knowledge_baseA

Manually trigger a knowledge base update from GitHub. Normally happens automatically every 30 minutes.

Inputs: force.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 6 tools

    Disambiguation4/5

    Most tools target distinct resource-action pairs, but search_knowledge_base and get_mcp_specification both cover MCP documentation and best practices and could be confused. The descriptions help by distinguishing broad search from canonical spec retrieval, so the ambiguity is limited.

    Naming Consistency5/5

    All tool names consistently follow a verb_noun pattern: search, list, get, add, check, update. Multiword objects like blocklist_entry and knowledge_base do not break the predictability of the naming convention.

    Tool Count5/5

    Six tools is a well-scoped count for a knowledge base MCP server. Each tool covers an essential workflow: searching, listing indexed content, retrieving the spec, managing blocklist entries, and triggering updates.

    Completeness3/5

    The core search, listing, spec retrieval, and update workflows are covered, but the blocklist lifecycle is incomplete—there is no way to remove an entry or list all blocked entries. An accidental blocklist addition becomes a dead end for the agent.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      B
      quality
      D
      maintenance
      An MCP server that enables interaction with Markdown knowledge bases, allowing users to search and retrieve content by tags, text, URL, or date range from their local markdown files.
      7
      91
      -
    • F
      license
      C
      quality
      D
      maintenance
      Git-backed MCP server for creating and maintaining an Obsidian-style markdown knowledge base with full CRUD, search, and git sync.
      7
      -
    • F
      license
      A
      quality
      B
      maintenance
      An MCP server that acts as a knowledge engine for software projects, delivering relevant context at the start of a task and accumulating knowledge at its end through tools like start_task, context, finish_task, remember, and search, with a file-based source of truth and optional semantic retrieval via Graphiti/Neo4j.
      5
      -