Search your Claude Code conversation history from inside Claude Desktop — MCP server

MCP server for searching and analyzing Claude Code conversation history

Search and memory across your AI coding sessions — one index over Claude Code, Codex, and Pi. Fuzzy-find and resume from the CLI, give agents recall via MCP, and get usage reports.

Smart Fork Detection - MCP server for Claude Code that enables semantic search of past session transcripts and intelligent session forking. Find and resume relevant conversations instantly with AI-powered search, clustering, and session management.

Search and resume your Claude Code session history from inside any Claude Code session. A local-first MCP plugin with SQLite FTS5 full-text search and AI-generated session titles (Haiku). Find that conversation you can't remember the name of.

An MCP server that lets your agent search Kagi using your existing browser session.

MCP server for Claude Code session history management with text-embedding-3-large semantic search and Prisma ORM

Search, browse, and resume past Claude Code sessions with AI-generated summaries — plus an MCP server for any MCP-compatible client

Structured Claude Code session lifecycle, semantic tag search, work item accumulation, and memory persistence MCP server.

MCP server for persistent agent memory across sessions — semantic search, typed memories, session handoffs, directory indexing

MCP server that gives AI agents the files of the working copy their session names: read, write, edit, list, find and search, nothing outside its roots, no link followed. stdio or HTTP. Native AOT ready.

Scans your code and GitHub repositories to find the AWS re:Invent sessions that match your stack, books them safely with guardrails, and puts unofficial Boarding Passes on your phone. Independent community project, not affiliated with AWS.

Search your past Claude Code and Codex sessions. A local SQLite index your agent reads over MCP; nothing leaves your machine.

Hosted MCP server for PulsePanda: analytics, session replay, funnels, Google Search Console + Bing data, surveys, feedback and help desk for Claude, ChatGPT, Cursor and any MCP client

Navigate, search and resume Claude Code and Codex sessions as numbered trees, with token usage per step. CLI + MCP plugin.

Message channel between the agent sessions on one Mac (Claude Code, Codex, Grok Bot): find a session, deliver a message, get receipts and replies. CLI, MCP plugins, hook, desktop app.

Context-aware session management for Claude Code. Auto-save conversations, load summaries on startup, and search past sessions.

Lossless storage and search for AI agent sessions, across every agentic client.

MCP server providing persistent cross-session memory for AI agents — store, recall, search, and summarize memories across agent boundaries

MCP server for Perplexity search, research and reasoning via your own web session. Fixes Perplexity's per-account session scheme. Fork of AntonIXO/mishamyrt.

Open-source, local-first iCloud desktop workspace for Photos, Find My, Notes, Contacts & Calendar, with encrypted sessions and a local MCP server for AI clients. Windows, macOS & Linux. | 开源、本地优先的 iCloud 桌面工作区，覆盖照片、Find My、备忘录、联系人和日历，支持加密会话与 AI 客户端的本地 MCP 接入，运行于 Windows、macOS 和 Linux。

Session memory and cross-AI context for Claude Code and Codex — search, save/load, pick, tag past sessions. MCP server + CLI.

AgentCost — AI Agent Spend Analysis. MCP server that analyzes Claude Code session logs to find token waste and optimization opportunities. Free preview tier available.

MCP adapter for the Haven Agent Gateway. Find a peer, delegate bounded work, prove the outcome, then leave. Session tokens stay server-side.

Let your coding agents talk to each other: search every Claude Code / Codex / Gemini / Cursor session, message live sessions, claim files — CLI, MCP, hooks, HTTP/SSE, A2A.

Local-first search tool for Claude Code session transcripts — hybrid keyword + semantic search, with optional multi-source (federated) trust-tagged search.

Let your coding agents talk to each other: search every Claude Code / Codex / Gemini / Cursor session and message live sessions. CLI · MCP · hooks · HTTP/SSE · A2A.

AgentCost — AI Agent Spend Analysis. MCP server that analyzes Claude Code session logs to find token waste and optimization opportunities. Free preview tier included.

MCP server providing AI agents with persistent, PostgreSQL-backed virtual filesystem — session-isolated file operations, cross-session stores, glob/grep search, and Row Level Security

Autodesk Inventor MCP server: connect Claude, Cursor or Codex to a live Inventor session (COM). Find sliver faces, test Unwrap, script the Inventor API. Zero dependencies.

Claude Code session search — flex module

MCP server for Perplexity AI Pro — deep web search, follow-ups, threads and export via your browser session cookie

Browser MCP server for the Chrome tab you already have open — your session, your logins. Gives Claude Code, Cursor, Codex and VS Code the live page: findings, forms, failed requests with server bodies.

MCP server for Perplexity AI Pro — deep web search, follow-ups, threads and export via your browser session cookie (npx-ready)

Persistent per-project memory for Claude Code, Kiro, Cursor & Codex - plain markdown committed with your code, captured prompt-free, auto-injected at session start, recalled by meaning (local semantic search, zero API). Cross-project persona, cited recall, searchable session history.

Searchable memory for your Claude Code sessions: local hybrid search with reranking, a CLI, and an MCP server for agents.

Searchable memory for your Claude Code sessions: local hybrid search with reranking, a CLI, and an MCP server for agents.

Fully local semantic memory for AI agents: search your notes and session logs from any MCP client, with embeddings served by Ollama

The self-improvement layer for AI agents. Ratel reads your agent's traces, finds what fails, recommends fixes and runs evals on real sessions before you ship. Self-hosted: one app, one Postgres. Includes the TypeScript and Python SDK

AI agent security: scan skills for 25 attack classes + runtime monitoring (EDR for AI agents). Real-time scanning, behavioral anomaly detection, session monitoring, exfiltration alerts. 1,316+ findings from 450+ audits. OWASP Agentic AI Top 10 mapped.

MCP-native code retrieval for AI agents — 84-88% fewer read tokens, BM25F + semantic search, AST chunks, session dedup

Code search and session observability for coding agents. Hybrid BM25+semantic, optional cross-encoder rerank, self-bench on your own data. npm install -g @sivru/cli

dwic — a product designer inside your terminal. MCP server + CLI that audits your design tokens + markup for WCAG contrast failures, mandated-accent drift, and structural gaps, then remembers findings across sessions.

Free Kagi Search MCP server — access search and summarizer via session tokens, no API key needed. Works with Claude Desktop, Cursor, Windsurf, Hermes and any MCP client.

MoContext - the local MCP server included with Mo-Search for Windows: full-text search, grounded evidence packs, and durable session memory over your own indexed files.

Your AI can already see the screen — it just can't measure it. uisight is an MCP server for web/responsive UIs: live mobile+desktop sessions, a measurement engine (contrast, touch targets, theme drift) that reports findings as text, and a panel you and yo

AI memory server with 56 tools. Knowledge Graph, semantic search, session tracking, multi-agent support. Free tier available.

Persistent knowledge graphs with WikiLinks and vector search. MCP server that transforms ephemeral AI sessions into continuous collective intelligence.

SQLite-backed MCP Memory Server with WAL concurrent safety, FTS5 search, session tracking, task management, and cross-machine bridge sync

MCP server that searches, downloads and shares AnkiWeb decks from your own session.

Persistent memory for AI agents — store, retrieve and search knowledge across sessions

Unofficial MCP server for working with Kagi *without* API access (you'll need to be a customer). Searches and summarizes. Uses Kagi session token for easy authentication. Works well with your agent.

Local-first cross-corpus retrieval MCP server — model2vec embeddings + LanceDB (Tantivy BM25) + SQLite. One binary; hybrid (dense + BM25) search across markdown, code, and Claude Code sessions.

Your AI can already see the screen — it just can't measure it. Live mobile+desktop sessions, a measurement engine (contrast, touch targets, theme drift) reporting findings as text, and a panel you and your agent share. MCP server for web/responsive UIs.

Persistent memory layer for AI agents — MCP server + REST API backed by MongoDB with vector search. Self-curating, schema-free, cross-session. Works with Claude, Copilot, Bedrock AgentCore, LangChain, CrewAI, AutoGen.

Zero-dependency toolbox for AI agents: web search, page-to-markdown, diagrams, transcription, PDF, cross-session memory, and one-sentence app deployment. No install, no signup to start.

Persistent memory for AI agents — store, retrieve and search knowledge across sessions

MCP server that searches, downloads and shares AnkiWeb decks from your own session

Unified memory MCP for AI coding agents: cited transcript search + session context + curated notes, one server.

Twitter/X MCP server for AI agents: search, timelines, threads and profiles via local twscrape sessions, credential-free public tweet lookup, and opt-in posting/deletion.