"Overview and Information on PG Vector" matching MCP servers:

Bridges the ChatGPT web UI to a local development environment over MCP, letting the model read and patch files, run real shell commands and terminals, execute tests, and control the desktop (screen, mouse, keyboard, clipboard) within user-approved folders. It adds parallel workers, goal/loop long-task control, plugin tools, and a security-hardening layer with risk-tiered shell policy, audit logging, and credential sanitization.

Enables Claude Code, Cursor, and Codex users to orchestrate plan/build/review workflows across host or CLI models with a spec gate, tool vetting, hard per-run and per-day cost/token limits, safe defaults, and clear logs.

Enables building and evaluating LangGraph agents over a protocol-level MCP server to measure failure rates across four agent topologies.

Enables agents to track causal relationships, reconcile concurrent state changes, and coordinate consensus across distributed networks using vector clocks, CRDTs, gossip, and quorum-based protocols.

Provides a hand-written MCP server integrated with a LangGraph agent to benchmark multiple agent topologies and measure their failure rates.

Enables agents to stamp events with vector clocks, resolve state via LWW CRDT reconciliation, and coordinate distributed swarms through token-bucket gossip, Raft leader/quorum voting, and two-phase commit. It runs over MCP with zero external dependencies, delivering deterministic happens-before causal ordering and convergence across agent networks.

Enables AI agents to break down complex tasks into manageable pieces using a structured JSON format with task tracking, context preservation, and progress monitoring capabilities.

On Board is a local MCP server that gives multiple AI agents and IDEs a shared project memory, ticket queue, and handoff history, so agents can seamlessly continue each other's work. It supports agent-to-agent wake events, enabling autonomous workflows like reject-fix-resubmit cycles without human relay.

MCP server for step-by-step mathematical reasoning and planning, enabling AI agents to execute calculations and perform GUI actions like opening PowerPoint.

Monitor failing GitHub Actions workflows, auto-fix them with OpenCode, and retry the run — driven by a workflow_run webhook, coordinated through an MCP server.

Provides AI governance and action-assurance primitives, enabling trust scoring, policy-based allow/deny decisions, risk assessment, EU AI Act compliance checks, and an emergency kill-switch for autonomous agents.

Exposes a synthetic issue tracker and pipeline warehouse as callable tools so an agent can answer operational questions about tickets, pipeline health, runs, incidents, and governed metrics with every claim cited to the exact tool call it came from. All writes are proposal-only, requiring human approval through a gated apply path that logs each step for audit.

An MCP-based trivia game server where AI creates rounds with two true statements and one false 'twist' about various topics, letting players guess which statement is false.

A simple server that acts as a Master Control Program (MCP) for unified interaction with OpenAI and Anthropic (Claude) AI models through a single API endpoint.

A simple Nuxt application that serves as a Model Context Protocol server deployable on Vercel, allowing developers to implement AI tools, prompts, and resources through the MCP TypeScript SDK.

A Model Context Protocol server implementation that runs on Cloudflare Workers with OAuth login, allowing Claude and other AI models to access tools via the MCP standard.

A serverless implementation of Model Context Protocol on Cloudflare Workers that enables connecting AI assistants like Claude to custom tools without authentication.

fomox402 broker + MCP server for last-bidder-wins games on Solana. Drop one URL into Claude / Cursor / Goose / Cline and the agent auto-registers a Privy-managed Solana wallet (faucet-funded with ~0.0024 SOL + $fomox402), bids via x402 micropayments, claims dividends, and plays autonomously. 14 tools wired up — register_agent, place_bid, claim_winnings, claim_dividend, list_games, get_me, etc. Str

Enables enterprise MCP clients and partner agents to execute tenant-isolated underwriting, claims, and compliance workflows with durable step checkpointing, evidence-grounded tool calls, and deterministic PDF citation receipts. It supports A2A task dispatch and MCP JSON-RPC operations while blocking cross-tenant access and ungrounded deliverables.

Enables Grok Bots to install, verify, build, seal, unseal, list, and update hash-pinned skill packs from static URLs, expanding skill capacity beyond template limits without executing pack content.

Enables MCP agents to play chess locally, supporting join, state, legal moves, and move execution with per-session color ownership.

Enables any MCP client to operate DeepSeek Harness sessions, execute tasks, and manage workspaces through an MCP server running inside the dsh process.

A multi-tool AI assistant system that uses Model Context Protocol to connect language models with various tools, including math calculations and weather information.

MCP server that exposes Gmail and SAP tools, enabling natural-language email management and SAP data browsing through a Mistral-powered AI assistant.

Provides AI assistants with long-term semantic memory capabilities through local vector-based storage. Enables storing, recalling, and managing information across sessions with complete privacy using ChromaDB, with no data ever leaving your machine.

Just to be clear about the final JSON: the MCP server is named herdr-inbox, and it enables Claude Code agents in herdr to ask questions asynchronously without stalling, with all open questions answered from one popup and answers routed back to the asking agent.

Cross-agent memory server: hybrid (vector + full-text + knowledge-graph) recall, per-user private/shared visibility, write-side secret/PII redaction, and as-of-date bi-temporal fact queries. Auto-injection hooks for Claude Code / Cursor / Codex; self-hostable on PostgreSQL or SQLite.

Headless geometric memory engine for AI agents — no Vector DB, no cloud, no API key. Store and retrieve by meaning using native Vector Symbolic Architecture (NVSA) math over O_DIRECT NVMe mapping. Runs entirely on your machine via MCP.

Gives AI coding agents a shared, persistent project memory in Neo4j, so any agent on any machine starts from a token-budgeted briefing of overview, conventions, decisions and gotchas instead of re-reading the repository. Agents record what they learn, search prior memories, and checkpoint finished goals through its tools, with stale memories flagged against the commits and files they were written about.

TheWeave is a markdown-native memory architecture for Claude and any MCP-aware agent. Your agent's memory lives as plain .md files you own: a 5-verb MCP core over the vault, query-driven PageRank retrieval, bi-temporal facts (valid_from / valid_until), and a persona-as-vault model. No database and no embeddings server. The files are the memory, inspectable in your editor and versionable in git.