Enables listing models and running non-streaming chat completions against RelayRouter's OpenAI-compatible API, so agents can discover available models and send chat requests through a key-configured MCP endpoint.

Provides a shared, repo-local memory that lets coding agents recall relevant decisions, conventions, gotchas, and open threads, save new entries, coordinate file claims, and cache file summaries across tools and sessions.

Serves the free Frankfurter exchange-rate API as MCP tools over stateless Streamable HTTP on Cloudflare Workers, letting clients list supported currencies, fetch the latest rates, and look up historical rates for a given date. Each OpenAPI operation becomes one tool, with argument validation and per-IP rate limiting.

It exposes a single slugify tool over remote MCP Streamable HTTP and a matching OpenAPI 3.1 endpoint, enabling clients to generate URL-friendly slugs through a stateless Cloudflare Worker.

Enables running NXOpen journals and Python scripts inside an already-open Siemens NX 2512 session from chat, with tools for pinging/checking the live bridge, creating and opening parts, and listing modules. It also adds a left-sidebar NX panel showing the bridge endpoint, available tools, and copy-ready commands.

Enables agents to analyze OpenAPI contracts for deterministic integration risks, plan auth, sync, action, and webhook candidates, and diff contract versions for likely breaking changes through read-only tools.

Enables agents to reach pump.fun's full API surface — official developer routes, bonding-curve reads, Solana RPC, and unsigned trade building — by writing JavaScript against one merged OpenAPI document, using just two tools (search and execute). Model-authored code runs in a network-less sandbox, so multi-step questions resolve in a single round trip while credentials stay on the host Worker.

Turns any OpenAPI spec into a single-tool MCP server where the model writes JavaScript against a typed api object in a QuickJS sandbox, so multi-step tasks run in one round trip and only the final result reaches context. Credentials, rate limiting, retries, write gating and audit logging stay on the host, outside the sandbox.

Keeps large tool outputs out of an agent's context window by spilling them to disk and handing back a short pointer instead. Lets the agent pull only what it needs — exact numbered line ranges read directly from disk, or verbatim relevant lines returned by a small model answering a question about the stored output, plus tools to open, list, and close documents.

Open-source adversary emulation for AI agents and MCP servers.

Self-hosted memory service for AI agents that work in teams, written in Rust: layered L0→L3 memory, async LLM distillation, hybrid BM25 + vector recall, and department/team/member isolation. SQLite or Postgres, any OpenAI-compatible LLM.

Enables AI agents to query Korean public data from OpenDART, data.go.kr and law.go.kr — corporate filings and financials, stock prices, apartment trades, business registration status, holidays, statutes in force on a given date, and court rulings. It corrects the live APIs' known traps (mislabeled periods, not-yet-in-force laws, cancelled trades, changed district codes) so answers come back right, with evidence.

Lets any MCP-capable AI agent call a hosted EdgePress site's REST API to browse and manage CMS content or store data, using a personal access token whose role and read-only flag decide what the agent can do. Supports Streamable HTTP at /api/mcp or local stdio via npx, with an OpenAPI spec lookup tool for discovering routes and request bodies.

Exposes Rekt Knockout and Minute trading over stdio as MCP tools: list markets, preview stake and payout after fees, and check open positions, plus opening and closing positions when a scoped session key or paper mode is configured. Signed operations always run under caller-defined risk limits and never use the owner's private key.

Exposes the Jupyter notebooks open in VS Code to MCP-compatible AI agents, letting them edit cells in the open editor and execute them in the live kernel without file conflicts. Agents can make partial edits, track stale cells, inspect variables, and manage kernels while preserving the user's interpreter choices and unsaved work.

Enables MCP-capable agent CLIs on macOS to reuse an installed, unmodified OpenAI Browser Runtime to drive a connected Chrome or Edge browser (or a host's in-app browser backend) through js, js_reset, and turn_ended tools. It stays a thin bridge that preserves the Runtime's approval and security boundaries, failing closed when the client cannot handle approval requests.

Enables users to view Alibaba Cloud account balances, credit limits, and cash voucher status through a persistent Codex panel or natural-language queries using read-only BSS OpenAPI access.

Enables Codex to delegate subtasks to concurrent background coding agents that can each run on any model provider supported by Pi, such as DeepSeek, Anthropic, Gemini, OpenRouter, or local models. Exposes MCP tools for listing models, spawning and waiting on agents, sending follow-ups, and aborting, backed by a live local web panel showing status, token usage, and streaming output.

Enables AI agents to open URLs in a persistent headless browser and interact with pages by clicking, typing, selecting, reading content, evaluating JavaScript, waiting for elements, and capturing screenshots.

Exposes a single authenticated MCP endpoint that federates to agents running on your own machines, letting you delegate coding jobs to be worked in fresh git worktrees and pushed to a branch, or proxy the stdio MCP servers installed there as tools. Agents dial out through a Cloudflare Tunnel and enforce your local policy, so no inbound ports are opened.

Enables agents to connect to and work with PostgreSQL, MySQL, Redis, SQLite, and MongoDB through a uniform tool surface for opening connections, running queries and commands, inspecting schemas, and managing documents.

Enables MCP clients to run read-only health checks against HTTP, TCP, SSL, and Docker targets defined in a single config.json, reporting status codes, latency, certificate expiry, and container state. Nothing is written, restarted, or modified — each probe just opens a connection, reads, and closes it.

Enables agents to create, edit, and share collaborative markdown documents hosted on the user's own Cloudflare account, with ordered writes and live updates to open editors.

Exposes a read_source tool that lets agents read cited tickets, docs, and files through the same path the checker verifies, so quoted business rules match their sources and stay in sync as those sources or their authors change. It also keeps undecided product decisions explicit as open questions rather than letting agents invent answers.