MCP server directory

Official Publora MCP server — schedule and publish posts across 10 social platforms (Twitter/X, LinkedIn, Instagram, Threads, TikTok, YouTube, Facebook, Bluesky, Mastodon, Telegram) from Claude, Cursor, or any MCP client. 18 tools for cross-platform posting, scheduling, media upload, and LinkedIn analytics. Hosted at mcp.publora.com.

Persistent codebase knowledge layer for AI coding agents. Pre-digests codebases into structured knowledge (symbols, dependency graphs, co-change patterns, architectural decisions) via tree-sitter native parsing (28 languages) and serves via MCP. 14 tools, ~85% token reduction. Works with Claude Code, Cursor, Codex, and any MCP client.

LLM-driven context and memory management with wide-recall + precise-reranking RAG architecture. Features multi-dimensional retrieval (vector/timeline/knowledge graph), short/long-term memory, and complete MCP support (HTTP/WebSocket/SSE).

9 MCP tools surfacing FalsifyLab public-market research data: DeFi yield farms (emissions-stripped APY), Hyperliquid vault leaderboard, SEC Form 4 insider buy clusters, material 8-K filings, macro tape (SPX/VIX/UST/DXY/GOLD/BTC/ETH), US spot crypto ETF flows, airdrop yield-gap detection, Polymarket whale positions, and confluence_today (cross-source signal alignment). Free tier requires no signup. Pro $19/mo for real-time + 100 results + 90d history. Install: `pip install falsifylab-alpha-mcp`.

Predictive port congestion signals for 15 global ports: congestion score (0-1), ETA delay in days, waiting vessels and a freight volatility index, computed by a DuckDB-backed engine with graceful fallback for unknown ports. Three tools: `get_port_risk`, `get_ports_risk`, `list_supported_ports`. Free tier, no API key. Remote endpoint at `https://aether-x-oracle-production.up.railway.app/mcp`, or run it locally with `uvx aetherx-mcp`. On the official MCP Registry as `io.github.belegante-byte/aetherx-mcp`.

Temporal knowledge graph for codebases. Captures decision traces, links test failures to code changes, learns co-edit patterns, predicts regression risk, and enforces learned constraints at the edit boundary via a PreToolUse hook. 22 MCP tools, 9 SQLite databases with FTS5, supports Python/TypeScript/JavaScript/Solidity/Go/Rust/Java. Install via `pip install world-model-mcp`.

Evibe gives you your own private, read-only MCP server. Connect your favorite AI assistant and ask it about your real holdings, performance, dividends and the wider market — in plain language, grounded in your actual numbers. Your private MCP endpoint mcp.evibe.com/u/••• The Model Context Protocol (MCP) is an open standard that lets an AI assistant call external tools to read real data. Evibe ships a hosted MCP server with 19 read-only tools, so an assistant like ChatGPT, Claude or Gemini can look at your live portfolio and the market — and answer questions about them. It is one of the first portfolio MCP servers you can connect to a mainstream AI assistant, and it is neutral across every broker you link.

6 tools · get_portfolio, get_portfolio_dividends

Persistent memory engine for AI coding agents. Stores architecture decisions, bug root causes, and project conventions across sessions. Single Go binary with embedded SQLite, FTS5 search, context assembly within token budgets, and autopilot setup for Claude Code, Kiro, and Cursor.

Persistent memory for AI agents with Ebbinghaus forgetting-curve decay, hybrid BM25+vector retrieval, and entity graph for multi-hop reasoning. Memories auto-prune by importance and recall rate. Built-in browser dashboard, multi-agent support, and `yourmemory ask` for zero-API-call local queries. `pip install yourmemory`

Second brain your agents read and write, over a git-backed markdown vault. Authority-aware search ranks superseded and archived notes below live ones (from frontmatter, no vector DB), so agents quote the current doc, not the dead one. Per-agent read-only or write tokens, a git audit trail of every change with diffs, a knowledge-graph dashboard, and Obsidian compatibility.

Five-level AI collaboration system with persistent memory and anticipatory capabilities. MCP-native integration for Claude and other LLMs with local-first architecture via MemDocs.

Official MCP server for Meser 10, an Israeli email and SMS marketing platform. All 61 tools are generated from the live API contract at start-up rather than hand-written, so coverage cannot drift when the platform ships an operation. Four permission tiers starting read-only (tools above the chosen tier are absent from `tools/list`, not merely refused), credentials are injected server-side and never appear in a tool schema, and a per-send recipient cap blocks an over-broad send. Listed in the official MCP registry as `io.github.meser10/meser10-mcp`. `npx -y @meser10/mcp-server`

Read and edit Word (.docx) documents with track changes, comments, footnotes, and structural validation. The only MCP server combining w:ins/w:del tracked changes, threaded comments, and footnotes with OOXML-level paraId validation and document auditing. 18 tools, Python 3.10+.

Private-by-default memory and context layer for agents with Go/Rust runtime, staged retrieval across fused data backends, and long-horizon context continuity.

Institutional memory for AI agents with real BFT consensus. 4 application validators vote on every memory before it's committed — no more storing garbage. 13 MCP tools, runs locally, works with any MCP-compatible model. Backed by 4 published research papers.

Connect Scrivener 3 writing projects to Claude and other AI assistants. 47 tools for document management, writing analysis, semantic search, character/plot memory, and content enhancement. Progressive skill loading, relationship engine with HMS triplets, and JS fallback for offline semantic search. `npm i -g scrivener-mcp`

Local-first semantic search over library docs. Single Go binary, MCP stdio, vector index pinned to the binary version. Like Context7 with the internet off. Pre-built index DB auto-fetched on first launch and SHA256-verified, then zero network. Also available as `docker run --rm -i ghcr.io/laradji/deadzone server`. Listed in the official MCP Registry as `io.github.laradji/deadzone`.

Multi-agent MCP server for genomic analysis — specialized AI agents analyze raw DNA files across 16 databases (ClinVar, GWAS, gnomAD, CPIC, AlphaMissense, and more) and coordinate findings through shared MCP tools. Privacy-first, runs locally.

Smart memory with exponential decay. Memories strengthen on access and fade when unused — solving the Karpathy problem of unbounded context growth. 7 tools, SQLite-based, zero dependencies.

Drive a real desktop NLE from any MCP client: place/trim/split clips, keyframes, effects, captions, role-based audio mixing, markers, checkpoints and hardware-accelerated export — the whole editing vocabulary, exposed as MCP tools, resources and prompts. Edits land live in the timeline the user is watching, every call is recorded in an Agent panel, and a multi-step batch can be rehearsed against a throwaway project clone (`dry_run`) before it touches anything.

Share the HTML your agent just wrote as a tracked link, then read back who opened it and which sections they read. Open source, AGPL-3.0, self-hostable, free for two links. `npx -y htmlradar-mcp`

Self-hosted knowledge store and memory layer for AI agents with knowledge graph, wiki-links, full-text search (FTS5), and agent memory with namespaces and TTL.

Personal knowledge graph for Claude on Neo4j. Typed entities (Person/Project/Decision/Preference/Concept), bi-temporal edge validity (`valid_at`/`invalid_at`), per-type weighted decay, contradiction detection, and a nightly "dream" extraction process. Local bge-small-en embeddings, no API keys. Optional OAuth 2.1 + Cloudflare Tunnel for cross-device use across Claude Code, Desktop, web, and iOS.

Get the LaTeX source of arXiv papers to handle mathematical content and equations

Transform 17 source types (docs, GitHub repos, PDFs, videos, Jupyter, Confluence, Notion, Slack/Discord) into AI-ready skills and RAG knowledge. 35 MCP tools for scraping, packaging, enhancing, and exporting to vector databases (Weaviate, Chroma, FAISS, Qdrant). Supports 16+ target platforms.

Let AI tools like Cursor, VS Code, or Claude Desktop answer questions using your product docs. Biel.ai provides the RAG system and MCP server.

Feature-complete Obsidian vault MCP server with 23 tools and 3 resources. Full-text search, note CRUD, frontmatter queries, tag management, backlinks, graph traversal (BFS up to 5 hops), orphan/broken link detection, and canvas support. Auto-detects vault, path traversal protection, MIT licensed.

SSE-enabled MCP server for remote Obsidian vault management with 29 tools for notes, directories, frontmatter, tags, search, and link operations. Docker-ready with health monitoring.

Lightweight local RAG MCP server for semantic vector search over markdown documents. Reduces token consumption by 40x with sqlite-vec and multilingual-e5-small embeddings. Supports filtered search by directory and filename patterns.

Your AI agents' home directory — privacy-first MCP server for portable AI identity. Configure once, use everywhere. It supports profile management, skills, resume import, and team sync.

Remote MCP server for public Instagram data: profiles and post feeds by handle with follower counts, captions, hashtags and mentions parsed, as JSON.

Precision visual captures for AI agents — real-colors terminal, syntax-highlighted code, browser, markdown, HTML, and git-diff as PNG/JPEG/PDF/GIF, plus multi-shot sequences and doc embedding. Rendered fully local via Playwright (SSRF-safe by default).

A local MCP server that generates animations using Manim.