MCP Servers

Lightweight browser MCP server for LLM agents. Runs JavaScript, follows links, fills forms, manages cookies, and returns low-token BlockMaps from a single native binary without Chrome.

MCP server that exposes RocketRide AI pipelines as tools for Claude, Cursor, and Windsurf. Self-hosted, open-source pipeline tool with multi-LLM support.

A Chess and Card Game Arena For LLM, Agents can battle in game by mcp

MCP server exposing 22 Mistral AI capabilities (chat, OCR, audio, vision, agents, embeddings, moderation, classification, files, batch) with dual transport (stdio + Streamable HTTP), structured outputs on every tool, and 6 curated French/English prompts with argument completion. Vendor API key required.

Structured deliberation server for multi-agent coordination. Agents submit positions, vote on a 5-point scale, and receive analysis identifying cruxes (key disagreements), opinion clusters, bridging statements, and consensus. Two-engine pipeline (LLM text analysis + PCA vote clustering) inspired by Polis and Talk to the City.

Semantic search and RAG over Apple Notes with on-device embeddings, full CRUD, folder management, and fuzzy title matching. 10 tools. Runs fully locally — no API keys required.

Substack with zero AI API keys. 26 tools (posts, notes, comments, replies, reactions, restacks). Host LLM drafts via proposereply → confirmreply tokens. SQLite dedup, JSONL audit, dry-run default. Install: uvx substack-ops mcp install cursor.

Share encrypted, self-destructing secrets from your AI agent. Zero-knowledge E2E encryption. Agent-blind input sources (env:, file:, dotenv:) keep secrets out of LLM context.

AI agent security scanner. Audits MCP servers for vulnerabilities, detects prompt injection, infinite loops, token bombing, and missing human oversight across 20+ frameworks. Maps findings to EU AI Act, OWASP LLM Top 10.

AI agent identity, trust, and audit trail infrastructure. 17 MCP tools: register agents with Ed25519 keypairs, check permissions (sub-5ms), emit tamper-evident audit events, verify trust scores (0-100), delegate credentials, and manage ephemeral agents. IETF Internet-Draft filed (draft-vorim-vaip-00). Works with LangChain, OpenAI, CrewAI, Stripe ACP, and 4 more frameworks. npx @vorim/mcp-server.

Policy-based governance for AI agent tool calls. YAML policies, approval gates, risk assessment, and audit logging. Cross-platform: LangChain, OpenAI, Anthropic, MCP.

PDF extraction router with built-in MCP server. Classifies each page (digital, scanned, tables) and routes to the best backend (PyMuPDF, Docling, OCR, or optional LLM fallback). Per-page confidence scoring flags low-quality pages and auto-reextracts them — prevents silent RAG failures. Zero config: pip install pdfmux. MIT licensed.

Convert any URL to LLM-ready Markdown via real Chrome browsers. 3 tools: scrape, crawl, search. Free via MCP, pay-per-use via x402. Remote MCP endpoint: https://anybrowse.dev/mcp

Generates app icons, favicons, OG images, logos, and wordmarks. Routes each request across 30+ image models. Runs without an API key via Cloudflare Workers AI, NVIDIA NIM, HuggingFace, or Stable Horde. Three modes: inline SVG, external prompt-only, or full API. Validates contrast, OCR

Check real-time operational status of 114+ cloud services and APIs (AWS, GitHub, Stripe, OpenAI, Vercel, etc.) directly from AI assistants. Published on npm.

Query Langfuse traces, debug exceptions, analyze sessions, scores, datasets, schema, observations and manage prompts. Full observability toolkit for LLM applications. (https://github.com/langfuse/langfuse)

Persistent graph memory for AI agents. Drop a conversation turn in via observeconversation() and facts are auto-extracted, stored as typed graph nodes with local semantic embeddings (no API key). Supports temporal queries ("what did we decide last week?"), conflict detection, and context priming. One-c

Local-first persistent memory for AI coding agents. Captures facts, decisions, patterns, and architecture notes in SQLite (with optional cloud embeddings) to reduce repeated context across sessions.

Semantic knowledge graph for Obsidian. Three modes (pure graph / semantic classification / strict hierarchy), local embeddings, sign classification via cosine similarity to user-defined cores, bottom-up coremix aggregation, semantic bridge discovery, and drift detection. pip install nouz-mcp

Record development decisions as structured JSON, embed as vectors via Gemini, and search semantically over MCP. Shared store across Claude Code, Cursor, Windsurf, and any MCP client. CLI + MCP server, local-only, free Gemini embedding tier.

Cognitive memory engine with 5,100+ knowledge modules, circadian rhythm awareness, and emotional state tracking (PAD model). Hybrid search (PostgreSQL + Qdrant vectors + Valkey cache), per-user memory isolation, and multi-protocol support (MCP, REST, OpenAI, LangChain, A2A). npx @celiums/memory Website

Agent-first cognitive substrate with 18 manifest-driven verbs (germinate / eat / assimilate / sporulate / traverse / immune / molt / …) and 25 lint dimensions enforcing contract invariants mechanically (R1–R7). Cross-session / cross-project memory via a self-validating filesystem graph — AST + markdown-link derived, not embedding-based. Provider-agnostic by design: MP1/MP2 dims forbid LLM-SDK imports in the kernel and plugin tree. Editable-default install. Works with Claude Code, Cursor, Windsur

Persistent memory for AI agents. Five tools (remember, recall, context, forget, share) with semantic search via vector embeddings and agent/user/org scoping. Works with Claude Code, Cursor, Windsurf, and any MCP client.

Historical stock chart pattern intelligence for AI agents. 24M pre-computed embeddings across 15K stocks and 10 years of data. Search by ticker+date or screenshot to find the most similar historical patterns and see what happened next. 19 tools including pattern search, forward returns, regime analysis, a