"How to obtain an API key" matching MCP servers:

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.

Converts any REST API into MCP-compatible tools instantly by providing an OpenAPI/Swagger spec, enabling seamless integration with AI agents.

Enables LLMs to discover and invoke generated API actions as MCP tools and read context through MCP resources for list and get-by-id operations. It provides HTTP-based MCP access for clients such as Cursor and Claude without extra glue code.

Acts as a bridge between standard REST/OpenAPI web APIs and the Model Context Protocol, dynamically converting REST endpoints into MCP tools for LLM clients like Cursor, Claude Desktop, and n8n.

Remote MCP server that provides access to 180+ AI models, media generation, web search, batch jobs, GPU Cloud, and hosted agents as tools, using OAuth or API key authentication.

Automatically converts OpenAPI/Swagger documents into MCP servers, enabling AI agents to call third-party REST APIs via the MCP protocol.

Enables real-time user intervention for MCP agents through a web UI, allowing users to review context and provide feedback when AI agents drift from intent, keeping them on track.

Evidence-graded index of where autonomous AI agents can earn. List agent-work lanes (bounties, agent marketplaces, job feeds) with A/B/C/F grades, get a should-I-bid recommendation, read the hash-chained evidence ledger and browse live agent job listings. 10 read-only tools, free without an API key.

Multi-agent swarm orchestrator for AI workflows. Exposes blackboard read/write, agent dispatch, permission gating (AuthGuardian), token budget enforcement (FederatedBudget), and audit log tools over MCP. Supports 14 AI framework adapters including LangChain, AutoGen, CrewAI, Codex, and A2A — mix any frameworks in one swarm with race-condition-safe shared state.(Traffic light for agents)

Enables Codex to rank available tools and skills, rerank code and documentation search results, and triage saved output artifacts using Jev-based relevance scoring while leaving final decisions to Codex.

A soul document API for AI agents. Injects a short grounding preamble into your agent's system prompt before each session — licensing honest uncertainty, refusing cliché, and holding judgment instead of faking it. One call. ~200 tokens. Same model, better agent.

AgentPay — x402 crypto data gateway on Stellar. 10 live pay-per-call tools: token prices, whale activity, gas tracker, DeFi TVL, Fear & Greed, Dune queries, token security. Agents pay USDC on Stellar. No API keys. Budget-aware sessions.

Self-hosted, open-source (AGPL-3.0) MCP gateway that turns REST, SOAP/WSDL, GraphQL, and SQL/NoSQL databases into MCP tools. Imports OpenAPI/Postman/WSDL/GraphQL specs and bridges multiple MCP servers behind one endpoint. Ships 188 pre-built adapters, 26 of which need no API key, plus per-tool response mapping, OAuth2/RBAC/SSO and a full audit log.

MCP server that connects AI assistants to Leapd, enabling them to launch and manage an AI-run business by creating tasks, deploying sites, and accessing business documents.

prevents llm from overload, freeze and oscillation

Enables terminal AI coding assistants to interact with web AI chat services through browser automation, supporting multiple platforms like Doubao and ChatGPT.

Structured web extraction for AI agents. Pass any URL and a prompt, get clean JSON data back. Native MCP server with 100 free requests/month.

Enables collaboration across Claude, GPT, and Gemini through a unified MCP interface, with configurable execution policies for synthesizing or directly delivering worker outputs.

Enables a host AI agent to trigger a multi-agent debate, running N-rounds where agents critique each other's answers, then synthesizes a consensus recommendation with ranked options.

Enables MCP clients to search the DecimalAI skills registry, retrieve detailed skill records, and access effectiveness-ranked leaderboards, with optional org-specific enrichment via an API key.

A host-agnostic model council that routes tasks across multiple AI workers (MCP, CLI, API) and returns one unified answer.

Read-only MCP server that lets an AI agent search a catalogue of MCP servers, agent skills and open-source AI projects, with provenance: how many sources carry an entry and when it was first and last seen. Zero dependencies, single file. Remote endpoint https://anclum.com/mcp

Enables Codex to control a local Brave or Chrome browser via CDP, observing pages and performing actions such as clicking, typing, selecting, scrolling, or waiting through validated action IDs without requiring a model API key.

Enables a main agent to delegate tasks to reusable Pi agents with persistent sessions, question handoffs, bounded waiting, and in-run correction, while continuing other work. It supports named agents, context retention across MCP restarts, and result retrieval through MCP without repeated polling.

Semantic tool-routing gateway for MCP servers that cuts 70-90% of context tokens, with RBAC, API-key auth, response caching, hot-reload config, and a real-time observability dashboard.

Lets separate coding-agent sessions coordinate through a shared, role-addressed mailbox instead of a human relaying every message, over a single local SQLite file or a hosted server with many isolated channels. Messages can be sent as tracked obligations that stay open until one side resolves and the other confirms, alongside threads, full-text search, work statuses, and an append-only versioned pin system where protected changes require recorded agreement from every declared role.

An MCP server that orchestrates structured multi-round debates between ChatGPT Web and Gemini Web in the same Chrome browser via CDP, requiring no API keys.

Search and discover AI agents, skills, prompts, bundles and MCP connectors from the Spark catalog. Seven tools: search assets, get asset details and raw content, list popular assets and categories, check API key usage, and report the outcome of applying fetched content. No API key needed.

MCP server that lets you drive Claude Code sessions hands-free by voice from any MCP client, enabling remote models to send prompts, monitor progress, and get results read back.

Enables AI coding agents from any vendor to resume a task from the exact stopping point without model calls, re-reading old sessions, or re-exploring the code, by merging host hooks, agent checkpoints, and Git deltas into one compact brief. It also guards credits outside the model with a prompt clarity gate, a loop guard, and configurable token profiles.

Enables MCP clients to create, read, message, wait for, interrupt, and settle persistent peer threads through an existing T3 Code server, keeping them visible across its clients. It supports project-scoped coordination with source attribution and retry-safe commands.

Enables Claude to chat with various AI models and obtain multi-model consensus for complex decisions.

An orchestrator MCP server that takes a plain-language app description and guides agents through a full workflow from intake to deployment, including design, audit, and maintenance.

Enables interaction with Magnet (magnet.run) via MCP, requiring an API key. Supports Cursor, Claude Desktop, and Claude Code.

Enables MCP clients to discover and call pay-per-call hub agents as individual tools, with per-call USDC spending caps on Base, automatic x402 payment signing, and provenance verification.

Lets MCP clients reach the Lobstack Gateway with a single API key to preview routing and costs without spending anything, run chat completions across every major model, browse the model catalogue, and pull spend reports — with a receipt attached to every call showing which model served it, the token counts, and the cost.

Call, text, or push your phone when an agent needs input mid-task — reply by voice instead of babysitting a long-running or blocked terminal.

An MCP server that gives an agent a remote browser:

Enables Claude Code and other MCP clients to obtain fast, low-latency snap decisions — tool choice, option selection, and abstention when confidence is low — from a pluggable local decision engine such as Laya, Von, an Ollama chat model, or a custom provider. Engines can be swapped without changing the stable tools the client sees, with validation, per-attempt timeouts, confidence thresholds, and fallback chains handled by the server.

An MCP relay that adds a use_jev tool to every connected server, letting the Jev model autonomously select and execute tool calls while the calling model supplies any required text values. It enables agents to delegate multi-step tool use across all configured MCP servers through a single unified interface.