Trust tools for agent-to-agent dealings — prove, vet, and bind with verifiable evidence (MCP server)

A queryable code graph for Laravel applications, exposed over MCP - dependency injection, container bindings, routes, views, Eloquent relations, connected the way generic AST tools cannot see.

FindAgent declarative MCP runtime — turns a FindAgent agent manifest into a live MCP server. Agents are declarative-only; this trusted runtime executes their tool bindings (no shipped code).

WebCite MCP Server - verify AI claims against authoritative sources, bind quotes back to their source passage, and extract document figures deterministically. Works with any MCP-compatible agent or tool.

🚀 MJOS v2.5.6 - Enterprise-Grade AI Operating System with Enhanced MCP Support & Bug Fixes. Perfect for Claude Desktop, Cursor, VS Code, and Augment. Features: Intelligent Memory System, Team Collaboration, Fixed MCP Tool Context Binding, Zero Resource L

Deterministic, verifiable orchestration for CLI coding agents (Claude Code, Codex, Gemini CLI, Aider, Cursor and 40+ more), exposed over MCP. Bernstein runs orchestration tasks in isolated git worktrees, records a lineage and replay journal for every run, and can anchor task claims, progress updates and posted artifacts in an opt-in HMAC-chained audit log. Tools: 14 are advertised at the default `standard` tool tier. Set BERNSTEIN_MCP_TOOL_TIER to change the tier: `core` advertises 5, `standard` advertises 14 (default), `all` advertises 18. Transports: stdio (default), Server-Sent Events, and streamable HTTP. Install and run: uvx --from bernstein bernstein mcp or pip install bernstein && bernstein mcp HTTP transport: bernstein mcp --transport http Authentication: the stdio transport needs none. The HTTP transport accepts a static bearer token via BERNSTEIN_MCP_TOKEN or BERNSTEIN_AUTH_TOKEN, and binds to loopback only when neither is set. Documentation: https://bernstein.readthedocs.io Requires Python 3.12 or newer. Package `bernstein` on PyPI, version 3.9.0.

**An SSH MCP server — a multitool that saves you and your AI agent time and tokens on debugging, development and server maintenance.** Run commands, move files, read logs and audit machines over SSH: a cloud VPS, a bare-metal box, or the BusyBox router in your closet. It uses the OpenSSH client already on your machine — your keys, your `~/.ssh/config`, your jump hosts, your agent forwarding. Nothing bundled, nothing to compile, no native bindings. **18 tools:** run commands and detach long ones as background jobs, move files and whole trees with sha256 verification, search and tail logs, snapshot load and disk, audit a machine in one round trip, check TLS certificates, inspect services. **Built for agents, not for humans.** Answers come back structured, a truncated result is reported as truncated instead of passing for a complete one, and destructive commands are stopped before they run. Works with Claude Code, Codex CLI, opencode, Gemini CLI, Qwen Code, Hermes and any MCP client.

Dynamically expose tools from proxied servers based on an Agent Persona

An open-source, local-first Model Context Protocol (MCP) server for **Secure Live Database Querying, Schema Inspection, AWS S3 Security Audits, and Cloudflare Infrastructure Control**.

Bind documentation claims to tiered code fingerprints. Catch stale CLAUDE.md, AGENTS.md and docs at write time inside Claude Code and Codex, with a tamper-evident history.

Guardrails for AI coding agents (Claude Code, Codex, OpenCode, Pi): an MCP server and hooks that verify issue claims, bind code reviews to exact commits, and gate merges. Local, single Rust binary.

Give coding agents the TypeScript compiler's actual reasoning — an MCP server and CLI that turn type errors into because-chains pointing at the declaration to fix. Also a library: explain-trees, inference bindings, conditional-type traces.

Skill + browser MCP for Claude Code and Codex: your app and browser reach domestic services over the real ISP while the agent stays on the VPN. Per-socket binding, per-host routing, no admin, nothing global.

Anchored memory MCP server for AI coding agents — binds decisions to code symbols, delivers context just-in-time. Works with Claude Code, Codex CLI, Cursor, Windsurf, Gemini CLI. No ML required. One SQLite file. 56x token compression.

Personal pre-indexed code knowledge graph for Java, Ruby, TypeScript and JavaScript — a call graph plus nine string-binding plugins for the wiring a call graph structurally cannot see: MyBatis, Camel, SQS, Kafka, HTTP routes, Spring events, GraphQL, gRPC, Flyway. Runs entirely offline.

Find the sentences in your docs that stopped being true. docsync binds documentation to the code, config and facts it describes, and `ds check` names every sentence whose code changed, moved or vanished, with the diff and the fix. Go CLI and library, MCP server for AI coding agents, LSP, GitHub Action, Hugo and Docusaurus.