Skip to main content
Glama
deenesjakoruzh
Cavinooo

claude-find

by Cavinooo
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Local

claude-find

Pull deep memory from across your Claude Code sessions — when you need it.

demo

Semantic search over all your past Claude Code sessions. Finds context by meaning and keywords. Searches the raw conversation transcripts, not compressed summaries, so Claude gets the full picture: reasoning, constraints, failed approaches, and decisions.

Setup

brew install bun ollama
bunx claude-find setup

setup starts Ollama, pulls the embedding model, sets session retention to permanent, and registers the MCP server with Claude Code. Sessions are indexed in the background on startup. Searches work immediately and return progressively more complete results as indexing continues.

Install Bun and Ollama, then run bunx claude-find setup. It detects your platform and guides you through anything missing.

Related MCP server: am-memory

Use it

In any Claude Code session:

/find that database migration we discussed last week
/find why we chose websockets over polling
/find the session where we kept getting timeout errors
/find refactoring the payment module across all projects

Claude searches your past sessions semantically, finds the relevant conversations, and synthesizes the context: what was tried, what failed, what constraints you set, and what decisions were made.

How it works

  1. Indexes all Claude Code session JSONL files from ~/.claude/projects/

  2. Extracts user + assistant messages, compact summaries, file paths from tool calls

  3. Enriches each chunk with metadata context (project, branch, files, date) for better retrieval

  4. Embeds conversation chunks using qwen3-embedding via Ollama (GPU accelerated)

  5. Searches with hybrid semantic + keyword (FTS5) merged via Reciprocal Rank Fusion

  6. Returns raw conversation chunks so Claude can synthesize with full context

After upgrading, run bunx claude-find index to rebuild the index with the latest improvements.

What makes this different

  • Searches raw transcripts. Nothing lost through compression.

  • Retroactive: works on all existing sessions immediately. No hooks needed.

  • Permanent history: setup disables Claude Code's 30-day session cleanup so your sessions are searchable forever.

  • Non-blocking: indexes in the background at startup. Searches work instantly, even mid-indexing.

  • Uses compact summaries: Claude's own session understanding, boosted in ranking.

  • Indexes tool call metadata: search by files touched, errors encountered.

  • Fast: Ollama + GPU keeps indexing fast and memory bounded.

Requirements

  • Bun runtime

  • Ollama (model auto-downloaded on first use)

  • Claude Code

License

MIT

Available Tools

1 tool
search_sessionsA

Search the full conversation history from past Claude Code sessions stored in ~/.claude/projects/. This tool has access to the complete raw transcripts of all previous sessions — including the actual back-and-forth discussion, reasoning, failed approaches, user constraints, and code decisions. Use this tool FIRST whenever the user mentions anything from a past session, asks 'what did we discuss', 'pull in context from', 'remember when we', 'how did we handle', or references any prior work. This tool searches semantically — the user doesn't need to remember exact words. Much more detailed than built-in memory.

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYesWhat to search for — natural language description of the past session or topic
max_sessionsNoMax sessions to return (default 3, max 5)
max_chunksNoMax conversation chunks per session (default 3, max 3)
scopeNo'current' searches only the current project (default), 'all' searches across all projects. Use 'all' when user says 'across all projects' or doesn't specify a project.current
project_filterNoFilter to a specific project by name (e.g. 'visk', 'myapp'). Use when user says 'in visk' or 'in the payments project'.

TDQS

A4.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. It discloses the scope of data ('complete raw transcripts', 'discussion, reasoning, failed approaches') and the semantic search nature. It does not mention any destructive actions or potential privacy concerns, but for a read-only search tool, the disclosure is sufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise with four sentences, starting with the core purpose and then usage guidance. Every sentence contributes meaning, though it could be slightly trimmed without loss.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description adequately explains the tool's function and when to use it, but it does not describe the return value format or content. The schema hints at output via parameters like max_sessions and max_chunks, but without an output schema, the description should explicitly state what is returned (e.g., matching sessions with chunks).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with detailed parameter descriptions. The tool description adds context about the underlying data ('complete raw transcripts') that enriches understanding of what the 'query' parameter searches over, going beyond the schema's literal description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool searches 'full conversation history from past Claude Code sessions' and specifies the exact storage location. It distinguishes itself from built-in memory by claiming to be 'much more detailed', which is useful even though no siblings are listed.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly tells when to use the tool first, listing example phrases like 'what did we discuss' and 'remember when we'. It also explains that searches are semantic, reducing the need for exact words, which is a clear usage recommendation.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 1 tool update
    • First observedsearch_sessions
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.4/5.0
Disambiguation5/5

With only one tool, there is no possibility of confusion between tools. The tool's purpose is clearly defined.

Naming Consistency5/5

The single tool name 'search_sessions' follows a consistent verb_noun pattern, though there are no other tools to compare against.

Tool Count3/5

A single tool for searching is borderline thin; most servers of this scope would benefit from at least 2-3 tools (e.g., list_sessions, get_session). The count is at the low end of reasonable.

Completeness4/5

The tool covers the core search functionality well, but lacks complementary tools such as listing available sessions or retrieving full transcripts by ID, which would make the surface more complete.

Maintenance

ActivityInactive
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • mcp-session-insight

    ArtLjn
    A
    license
    A
    quality
    C
    maintenance
    Enables AI assistants to query and analyze past Claude Code sessions, providing structured insights like file changes, decisions, errors, and git history across projects.
    11
    20
    1
    MIT

  • am-memory

    danielwanwx
    A
    license
    Not graded
    quality
    D
    maintenance
    Persistent memory for Claude Code — a self-evolving knowledge layer that survives across sessions, grows from every conversation, and surfaces relevant context automatically.
    14
    MIT

  • context-bridge

    zachvp
    A
    license
    Not graded
    quality
    A
    maintenance
    Enables Claude Code to search and retrieve past chat history from Claude.ai exports and Claude Code sessions, allowing the AI to reference previous conversations and decisions.
    MIT

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Cavinooo/claude-find'

If you have feedback or need assistance with the MCP directory API, please join our Discord server