Skip to content
Back to search

claude-historian-mcp

πŸ“œ An MCP server for conversation history search and retrieval in Claude Code

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/vvkmnn--claude-historian-mcp/badge.svg)](/listings/vvkmnn--claude-historian-mcp)

HTML

<a href="/listings/vvkmnn--claude-historian-mcp"><img src="/api/listings/vvkmnn--claude-historian-mcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

**Requirements:**

**From shell:**

claude mcp add claude-historian-mcp -- npx claude-historian-mcp

**From inside Claude** (restart required):

Add this to our global mcp config: npx claude-historian-mcp

Install this mcp: https://github.com/Vvkmnn/claude-historian-mcp

**From any manually configurable `mcp.json`**: (Cursor, Windsurf, etc.)

{
  "mcpServers": {
    "claude-historian-mcp": {
      "command": "npx",
      "args": ["claude-historian-mcp"],
      "env": {}
    }
  }
}

There is **no `npm install` required** -- no external dependencies or local databases, only search algorithms.

However, if `npx` resolves the wrong package, you can force resolution with:

npm install -g claude-historian-mcp

> **renamed:** This project was renamed from `claude-historian` to `claude-historian-mcp`. Existing users should update your install command and MCP config args to `claude-historian-mcp`.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md Β· README Β· 353 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <img align="right" src="claude-historian.svg" alt="claude-historian-mcp" width="220">
  2. # claude-historian-mcp
  3. An [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) server for searching your [Claude Code](https://docs.anthropic.com/en/docs/claude-code) conversation history. Find past solutions, track file changes, and learn from previous work.
  4. <br clear="right">
  5. ![claude-historian-mcp](demo/demo.gif)
  6. [![npm version](https://img.shields.io/npm/v/claude-historian-mcp.svg)](https://www.npmjs.com/package/claude-historian-mcp) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) [![TypeScript](https://img.shields.io/badge/TypeScript-007ACC?logo=typescript&logoColor=white)](https://www.typescriptlang.org/) [![Node.js](https://img.shields.io/badge/node-%3E%3D20-brightgreen)](https://nodejs.org/) [![Claude](https://img.shields.io/badge/Claude-D97757?logo=claude&logoColor=fff)](#) [![GitHub stars](https://img.shields.io/github/stars/Vvkmnn/claude-historian-mcp?style=social)](https://github.com/Vvkmnn/claude-historian-mcp) ![CodeRabbit Pull Request Reviews](https://img.shields.io/coderabbit/prs/github/Vvkmnn/claude-historian-mcp?utm_source=oss&utm_medium=github&utm_campaign=Vvkmnn%2Fclaude-historian-mcp&labelColor=171717&color=FF570A&link=https%3A%2F%2Fcoderabbit.ai&label=CodeRabbit+Reviews)
  7. ---
  8. ## install
  9. **Requirements:**
  10. [![Claude Code](https://img.shields.io/badge/Claude_Code-555?logo=data:image/svg%2bxml;base64,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)](https://claude.ai/code)
  11. **From shell:**
  12. ```bash
  13. claude mcp add claude-historian-mcp -- npx claude-historian-mcp
  14. ```
  15. **From inside Claude** (restart required):
  16. ```
  17. Add this to our global mcp config: npx claude-historian-mcp
  18. Install this mcp: https://github.com/Vvkmnn/claude-historian-mcp
  19. ```
  20. **From any manually configurable `mcp.json`**: (Cursor, Windsurf, etc.)
  21. ```json
  22. {
  23. "mcpServers": {
  24. "claude-historian-mcp": {
  25. "command": "npx",
  26. "args": ["claude-historian-mcp"],
  27. "env": {}
  28. }
  29. }
  30. }
  31. ```
  32. There is **no `npm install` required** -- no external dependencies or local databases, only search algorithms.
  33. However, if `npx` resolves the wrong package, you can force resolution with:
  34. ```bash
  35. npm install -g claude-historian-mcp
  36. ```
  37. > **renamed:** This project was renamed from `claude-historian` to `claude-historian-mcp`. Existing users should update your install command and MCP config args to `claude-historian-mcp`.
  38. ## [skill](.claude/skills/claude-historian)
  39. Optionally, install the skill to teach Claude when to proactively use historian:
  40. ```bash
  41. npx skills add Vvkmnn/claude-historian-mcp --skill claude-historian --global
  42. # Optional: add --yes to skip interactive prompt and install to all agents
  43. ```
  44. This makes Claude automatically check your history before web searches, when encountering errors, or at session start. The MCP works without the skill, but the skill improves discoverability.
  45. ## [plugin](https://github.com/Vvkmnn/claude-emporium)
  46. For automatic history search with hooks and commands, install from the [claude-emporium](https://github.com/Vvkmnn/claude-emporium) marketplace:
  47. ```bash
  48. /plugin marketplace add Vvkmnn/claude-emporium
  49. /plugin install claude-historian@claude-emporium
  50. ```
  51. The **claude-historian** plugin provides:
  52. **Hooks** (targeted, zero overhead on success):
  53. - Before WebSearch/WebFetch β†’ Check `search scope="similar"`
  54. - Before EnterPlanMode β†’ Check `search scope="plans"`
  55. - Before Task agents β†’ Check `search scope="tools"`
  56. - After Bash errors β†’ Check `search scope="errors"`
  57. **Command:** `/historian-search <query>`
  58. Requires the MCP server installed first. See the emporium for other Claude Code plugins and MCPs.
  59. ## features
  60. [MCP server](https://modelcontextprotocol.io/) that gives Claude access to your conversation history. Two tools, 11 scopes, zero dependencies.
  61. Runs locally (with cool shades `[βŒβ– _β– ] πŸ“œ`):
  62. #### `search`
  63. Search across conversations, files, errors, plans, config, tasks, sessions, tools, similar queries, and memories.
  64. ```
  65. search query="docker auth error" # default scope: all
  66. search query="fix build" scope="conversations" # past solutions
  67. search query="ENOENT" scope="errors" # error patterns + fixes
  68. search query="auth" scope="plans" # implementation plans
  69. search query="hooks" scope="config" # rules, skills, CLAUDE.md
  70. search query="git push" scope="similar" # related questions asked before
  71. search query="Edit" scope="tools" # tool usage workflows
  72. search filepath="package.json" scope="files" # file change history
  73. search scope="sessions" # recent sessions
  74. search scope="memories" # project memory files
  75. search query="deploy" scope="all" detail_level="detailed" # full context
  76. search query="auth" timeframe="7d" project="my-app" # filtered
  77. ```
  78. ```json
  79. πŸ“œ ── search "docker auth" ── 5 results Β· 405 tokens
  80. {
  81. "results": [{
  82. "type": "assistant",
  83. "ts": "2h ago",
  84. "content": "Fixed Docker auth by updating registry credentials...",
  85. "project": "my-app",
  86. "score": 100,
  87. "ctx": { "filesReferenced": ["docker-compose.yml"], "toolsUsed": ["Edit", "Bash"] }
  88. }]
  89. }
  90. ```
  91. ```json
  92. πŸ“œ ── files "package.json" ── 92 operations Β· 1594 tokens
  93. {
  94. "filepath": "package.json",
  95. "operations": [{
  96. "type": "edit",
  97. "ts": "1d ago",
  98. "changes": ["Changed: \"version\": \"1.0.3\" β†’ \"version\": \"1.0.4\""],
  99. "content": "Updated version for release"
  100. }]
  101. }
  102. ```
  103. ```json
  104. πŸ“œ ── tools "Bash" ── 5 patterns Β· 427 tokens
  105. {
  106. "tool": "Bash",
  107. "patterns": [{
  108. "name": "Bash",
  109. "uses": 10,
  110. "workflow": "$ npm run build 2>&1",
  111. "practice": "Used with: ts, js, json, md files"
  112. }]
  113. }
  114. ```
  115. #### `inspect`
  116. Get an intelligent summary of any session by ID (full UUID or short prefix).
  117. ```
  118. inspect session_id="latest" # most recent session
  119. inspect session_id="d537af65" # short prefix works
  120. inspect session_id="d537af65" focus="files" # only file changes
  121. inspect session_id="d537af65" focus="tools" # only tool usage
  122. inspect session_id="d537af65" focus="solutions" # only solutions
  123. ```
  124. ```json
  125. πŸ“œ ── inspect my-app (68d5323b)
  126. {
  127. "session": {
  128. "id": "68d5323b",
  129. "ts": "2h ago",
  130. "duration": 45,
  131. "messages": 128,
  132. "project": "my-app",
  133. "tools": ["Edit", "Bash", "Read"],
  134. "files": ["src/auth.ts", "package.json"],
  135. "accomplishments": ["fixed auth bug", "added unit tests"],
  136. "decisions": ["chose JWT over sessions"]
  137. }
  138. }
  139. ```
  140. ## methodology
  141. How [claude-historian-mcp](https://github.com/Vvkmnn/claude-historian-mcp) [works](https://github.com/Vvkmnn/claude-historian-mcp/tree/master/src):
  142. ```
  143. "docker auth" query
  144. |
  145. β”œβ”€> Parallel Processing (search.ts:174): 15 projects Γ— 10 files concurrently
  146. | β€’ Promise.allSettled for 6x speed improvement
  147. | β€’ Early termination when sufficient results found
  148. | β€’ Enhanced file coverage with comprehensive patterns
  149. |
  150. β”œβ”€> Enhanced Classification (search.ts:642): implementation β†’ boost tool workflows
  151. | β€’ Workflow detection for tool sequences (Edit β†’ Read β†’ Bash)
  152. | β€’ Semantic boundary preservation (never truncate mid-function)
  153. | β€’ Claude-optimized formatting with rich metadata
  154. |
  155. β”œβ”€> Smart Ranking (utils.ts:267):
  156. | β”œβ”€> Core Terms (scoring-constants.ts): "docker" +10, "auth" +10
  157. | β”œβ”€> Supporting Terms: context words +3 each
  158. | β”œβ”€> Tool Usage: Edit/Bash references +5
  159. | β”œβ”€> File References: paths/extensions +3
  160. | └─> Project Match: current project +5
  161. |
  162. β”œβ”€> Results sorted by composite score:
  163. | β€’ "Edit workflow (7x successful)" (2h ago) ***** [score: 45]
  164. | β€’ "Docker auth with context paths" (yesterday) **** [score: 38]
  165. | β€’ "Container debugging patterns" (last week) *** [score: 22]
  166. |
  167. └─> Return Claude Code optimized results
  168. ```
  169. **Core optimizations:**
  170. - [parallel processing](https://github.com/Vvkmnn/claude-historian-mcp/blob/master/src/search.ts#L174): `Promise.allSettled` for 6x speed improvement across projects and files
  171. - [workflow detection](https://github.com/Vvkmnn/claude-historian-mcp/blob/master/src/search.ts#L1122): Captures tool sequences like "Edit β†’ Read β†’ Bash" patterns
  172. - [enhanced file matching](https://github.com/Vvkmnn/claude-historian-mcp/blob/master/src/search.ts#L793): Comprehensive path variations with case-insensitive matching
  173. - [intelligent deduplication](https://github.com/Vvkmnn/claude-historian-mcp/blob/master/src/search-helpers.ts#L40): Content-based deduplication preserving highest-scoring results
  174. - [intelligent truncation](https://github.com/Vvkmnn/claude-historian-mcp/blob/master/src/formatter.ts#L46): Never truncates mid-function or mid-error
  175. - [Claude-optimized formatting](https://github.com/Vvkmnn/claude-historian-mcp/blob/master/src/formatter.ts#L26): Rich metadata with technical content prioritization
  176. **Search strategies:**
  177. - **[JSON streaming parser](https://en.wikipedia.org/wiki/JSON_streaming)** ([parseJsonlFile](https://github.com/Vvkmnn/claude-historian-mcp/blob/master/src/parser.ts#L16)): Reads Claude Code conversation files on-demand without full deserialization
  178. - **[LRU caching](<https://en.wikipedia.org/wiki/Cache_replacement_policies#Least_recently_used_(LRU)>)** ([messageCache](https://github.com/Vvkmnn/claude-historian-mcp/blob/master/src/search.ts#L27)): In-memory cache with intelligent eviction for frequently accessed conversations
  179. - **[TF-IDF inspired scoring](https://en.wikipedia.org/wiki/Tf%E2%80%93idf)** ([calculateRelevanceScore](https://github.com/Vvkmnn/claude-historian-mcp/blob/master/src/utils.ts#L267)): Term frequency scoring with document frequency weighting for relevance
  180. - **[Query classification](https://en.wikipedia.org/wiki/Text_classification)** ([classifyQueryType](https://github.com/Vvkmnn/claude-historian-mcp/blob/master/src/search.ts#L642)): Naive Bayes-style classification (error/implementation/analysis/general) with adaptive limits
  181. - **[Edit distance](https://en.wikipedia.org/wiki/Edit_distance)** ([calculateQuerySimilarity](https://github.com/Vvkmnn/claude-historian-mcp/blob/master/src/search-helpers.ts#L157)): Fuzzy matching for technical terms and typo tolerance
  182. - **[Exponential time decay](https://en.wikipedia.org/wiki/Exponential_decay)** (getTimeRangeFilter): Recent messages weighted higher with configurable half-life
  183. - **[Parallel file processing](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Promise/allSettled)** ([getErrorSolutions](https://github.com/Vvkmnn/claude-historian-mcp/blob/master/src/search.ts#L985)): Concurrent project scanning with early termination for 0.8s response times
  184. - **[Workflow pattern recognition](https://en.wikipedia.org/wiki/Sequential_pattern_mining)** ([getToolPatterns](https://github.com/Vvkmnn/claude-historian-mcp/blob/master/src/search.ts#L1122)): Detects tool usage sequences and related workflows for learning
  185. - **[Enhanced file context](<https://en.wikipedia.org/wiki/Path_(computing)>)** ([findFileContext](https://github.com/Vvkmnn/claude-historian-mcp/blob/master/src/search.ts#L793)): Multi-project search with comprehensive path matching
  186. - **[Content-aware truncation](https://en.wikipedia.org/wiki/Text_segmentation)** ([smartTruncation](https://github.com/Vvkmnn/claude-historian-mcp/blob/master/src/formatter.ts#L46)): Intelligent content boundaries over arbitrary character limits
  187. - **[Technical content prioritization](https://en.wikipedia.org/wiki/Information_extraction)** ([BeautifulFormatter](https://github.com/Vvkmnn/claude-historian-mcp/blob/master/src/formatter.ts#L26)): Code blocks, errors, and file paths get full preservation
  188. - **[Query similarity clustering](https://en.wikipedia.org/wiki/Cluster_analysis)** ([findSimilarQueries](https://github.com/Vvkmnn/claude-historian-mcp/blob/master/src/search.ts#L912)): Semantic expansion and pattern grouping for related questions
  189. **Design principles:**
  190. - **Universal engine** -- single search backend for all Claude Code conversations
  191. - **Parallel processing** -- concurrent file scanning across session directories
  192. - **Semantic expansion** -- query synonyms and related terms for better recall
  193. - **Zero dependencies** -- only `@modelcontextprotocol/sdk`, no databases required
  194. - **Offline** -- never leaves your machine, scans local JSONL files only
  195. **File access:**
  196. - Reads from: `~/.claude/conversations/`
  197. - Zero persistent storage or indexing
  198. - Never leaves your machine
  199. **Performance:** See [PERFORMANCE.md](./PERFORMANCE.md) for benchmarks, optimization history, and quality scores.
  200. ## alternatives
  201. Every conversation history tool either loads context always (burning tokens when unused) or requires external runtimes and databases. Historian searches on-demand with zero dependencies.
  202. | Feature | **historian** | Claude Memory | claude-mem | deja | conversation-search |
  203. | ----------------------- | ----------------------- | ----------------------- | -------------------------------- | ------------------- | ---------------------------- |
  204. | **Dependencies** | **Zero** | Built-in | Bun + Python + SQLite + Chroma | Python | Rust toolchain |
  205. | **Background service** | **No** | No | Yes (port 37777) | No | No |
  206. | **Writes to disk** | **Never** | Yes (auto-memory files) | Yes (SQLite + Chroma DB) | Yes (breadcrumbs) | Yes (~10% index overhead) |
  207. | **Session startup** | **0 tokens** | ~200 lines loaded | 5-8k tokens every session | Skill prompt loaded | 0 tokens |
  208. | **Token cost (idle)** | **0** | 200 lines/session | 5-8k/session | Skill prompt/session| 0 |
  209. | **Search algorithms** | **[12](#methodology)** | None (file read) | Vector + keyword | Weighted signals | BM25 full-text |
  210. | **Fuzzy matching** | **Yes** | No | Yes (vector similarity) | No | No |
  211. | **Workflow detection** | **Yes** | No | No | No | No |
  212. | **Raw conversations** | **Yes** | No (summaries only) | No (compressed observations) | Yes | Yes (filtered) |
  213. | **Maintenance** | **Zero** | Zero | Worker daemons, migrations | Skill config | Index rebuilds |
  214. **[Claude Memory](https://docs.anthropic.com/en/docs/claude-code/memory)** -- Claude's built-in memory (`CLAUDE.md` + auto-memory). Persists project rules and preferences across sessions. Forward-looking ("always use ESM imports"); not conversation search. **Complementary**: memory for rules, historian for past solutions.
  215. **[claude-mem](https://github.com/thedotmack/claude-mem)** -- Plugin that captures observations via lifecycle hooks, compresses them into SQLite + Chroma, and loads context every session. Requires Bun, Python, and a background worker on port 37777. Real-world testing (270+ sessions): 95% of sessions never query history -- always-on tools pay 5-8k tokens per session regardless. Historian pays 0 tokens idle, 500-2k per query, saving ~475k tokens over 100 sessions. Known issues: creates stub session files that break `--continue`, worker daemon version conflicts, security hooks blocking valid edits.
  216. **[deja](https://github.com/kateleext/deja)** -- Python skill that indexes sessions by episodes and accomplishments. Uses weighted signal ranking (todos > files > text). Requires Python and TodoWrite integration.
  217. **[conversation-search](https://github.com/ticpu/claude-conversation-search-mcp)** -- Rust MCP server using Tantivy BM25 full-text search. Fast indexing (~1000 conversations/second) but requires Rust toolchain and persistent disk index.
  218. ## desktop
  219. **Note:** Claude Desktop stores conversations server-side, not locally. The local LevelDB files (`~/Library/Application Support/Claude/`) contain only session tokens, UI preferences, and Intercom state - not conversation content. Claude Desktop support is also blocked by [LevelDB locks](https://github.com/Level/level#open) and [Electron sandboxing](https://www.electronjs.org/docs/latest/tutorial/sandbox).
  220. This means **local history search for Claude Desktop is not currently possible**. This project focuses on **Claude Code**, which stores full conversation history locally in `~/.claude/projects/`.
  221. You may get some Claude Desktop from Claude Code, but **only when the Claude app is closed**. Furthermore A DXT package and build is available for future compatibility; further investigations are ongoing. Feel free to test with it.
  222. ## development
  223. ```bash
  224. git clone https://github.com/Vvkmnn/claude-historian-mcp && cd claude-historian-mcp
  225. npm install && npm run build
  226. npm test
  227. ```
  228. **Package requirements:**
  229. - **Node.js**: >=20.0.0 (ES modules)
  230. - **Runtime**: `@modelcontextprotocol/sdk`
  231. - **Zero external databases** -- works with `npx`
  232. **Development workflow:**
  233. ```bash
  234. npm run build # TypeScript compilation with executable permissions
  235. npm run dev # Watch mode with tsc --watch
  236. npm run start # Run the MCP server directly
  237. npm run lint # ESLint code quality checks
  238. npm run lint:fix # Auto-fix linting issues
  239. npm run format # Prettier formatting (src/)
  240. npm run format:check # Check formatting without changes
  241. npm run typecheck # TypeScript validation without emit
  242. npm run test # Lint + type check
  243. npm run prepublishOnly # Pre-publish validation (build + lint + format:check)
  244. ```
  245. **Git hooks (via Husky):**
  246. - **pre-commit**: Auto-formats staged `.ts` files with Prettier and ESLint
  247. - **pre-push**: Runs full validation (format, lint, type-check, build) before push
  248. Contributing:
  249. - Fork the repository and create feature branches
  250. - Test with large conversation histories before submitting PRs
  251. - Follow TypeScript strict mode and [MCP protocol](https://modelcontextprotocol.io/specification) standards
  252. Learn from examples:
  253. - [Official MCP servers](https://github.com/modelcontextprotocol/servers) for reference implementations
  254. - [TypeScript SDK](https://github.com/modelcontextprotocol/typescript-sdk) for best practices
  255. - [Creating Node.js modules](https://docs.npmjs.com/creating-node-js-modules) for npm package development
  256. ## license
  257. [MIT](LICENSE)
  258. <hr>
  259. <a href="https://en.wikipedia.org/wiki/Cesare_Maccari"><img src="logo/appius-claudius.jpg" alt="Appius Claudius Caecus in the Senate -- Cesare Maccari" width="100%"></a>
  260. <p align="center">
  261. _**[Appius Claudius Caecus in the Senate](https://en.wikipedia.org/wiki/Cesare_Maccari)** by **[Cesare Maccari](https://en.wikipedia.org/wiki/Cesare_Maccari)** (1888). Roman statesman and father of Latin prose._
  262. </p>

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.