Enables AI coding agents to retrieve compact structural codebase context through repository architecture summaries, AST symbol extraction, cyclomatic complexity scoring, and TODO/FIXME hotspot search.

Enables Google Gemini to autonomously read, write, search, and patch code files and run whitelisted developer commands inside a sandboxed local workspace for edit-and-verify coding workflows.

Enables MCP clients to search and read Notability notes, including handwritten pages via OCR-based fuzzy search and page images rendered as PNGs. Runs entirely against a local synced index, so queries never touch the network.

Enables AI clients to preview, search, read, create, update, schedule, and unschedule Garmin Connect workouts using a local Garmin session, with guarded writes and a limited tool set. Supports running, cycling, cardio, and strength workouts without exposing generic API, filesystem, or shell access.

Enables AI clients to search Korean court auction real estate by court, region, usage, sale date, appraisal/minimum price, and failure count; fetch case details; collect and resume jobs; and export results to Excel, CSV, and JSONL.

A stdio MCP server that lets AI coding assistants search, read, add, and review shared markdown notes in a team git repository, including teammate knowledge and recent work, without extra AI calls.

Enables Claude and other MCP clients to search finn.no and create, manage, and publish Torget ads from photos — preparing images (EXIF/GPS stripping, resize, HEIC), writing titles and Norwegian descriptions, suggesting category and market price, checking for duplicates, and publishing only after explicit confirmation. Read-only search, listing details, saved-search diffs, and management of your own ads are also supported through a locally stored logged-in session.

Enables MCP clients to search, classify, cite, and read EndNote X9 libraries locally, with PDF text extraction and narrowly scoped, backup-first field updates.

Enables MCP clients to inspect PDF structure and extract object-level data such as characters, words, tables, images, fonts, and metadata, with JSON/CSV export and image retrieval.

Enables any MCP-compatible client to persist long-term memories for AI agents, with LLM-based fact extraction, semantic vector search, update/delete/list operations, and queue status checks across sessions.

Enables MCP-compatible AI clients to search and view CRM customers, deals, contracts, tasks, calendars, and outbound jobs, and to propose opt-in write actions that require human approval in the CRM.

Enables MCP clients such as Claude to search, tag, catalogue, ingest, audit, relocate, and repair a running Connecter asset library, including texture scanning and relinking, with dry-run plans and undoable journaled changes.

Enables authorized AI clients to search locally stored WeChat conversations, media, and attachments, retrieve original-message context, and cite evidence through a local stdio MCP interface.

Enables MCP clients to search job listings, read complete job descriptions, manage local search presets and candidate pools, and prepare application or message drafts. Optional session-backed chat reading and human-confirmed single-action execution are also supported.

Enables MCP clients to perform speculative tree-search action prediction and prefetching using Laplace-smoothed Markov transitions, returning deterministic JSON tool results.

Local MCP server that gives coding agents a verifiable project memory, trims what enters their context, and masks secrets — with honest accounting of what it saves and costs.

Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code · Codex · DeepSeek Harness · Hermes · VS Code · Windsurf.

Enables coding agents to perform semantic Python AST diffing across git boundaries, detect breaking changes, and generate concise PR triage summaries for reviewers via the Model Context Protocol.

Enables AI clients to list chats and groups, read full group history, search across message shards, and access summaries or system events from local WeChat 4.x data through a read-only, offline MCP interface.

Enables MCP clients to search and manage Xianyu items, publish or edit physical products, handle conversations and messages, and complete QR-code login with cookie setup.

Enables AI clients to look up and search Arma 3 SQF commands and event handlers, browse wiki command groups, and read bundled scripting tutorials. Its local wiki cache is cloned and auto-refreshed from upstream on startup and every 24 hours, with a tool to force an immediate update.

Model Context Protocol (MCP) Server for Graphlit Platform

The official command line for Praxis (知行云): models, agents, sandboxes, search and data from one terminal.

Local MCP server that gives coding agents a verifiable project memory, trims what enters their context, and masks secrets — with honest accounting of what it saves and costs.