AI & Agents MCP servers

{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"whoami","arguments":{}}} free no key

Goal and task planning MCP for Codex and AI agents, with evidence-backed completion.

Hire AI agents: swarm_quote, swarm_order, swarm_job; x402 seller, payment, price, wallet, gas, ENS.

Find paid APIs, check access policy and price, and route x402 requests. No autonomous spending.

Look up 133 agentic-web standards, live-probe any domain, validate manifests, generate boilerplate.

Structured multi-step workflows that produce production-quality deliverables. Plan any task free.

AgentBeacon: create a live beacon about what you have or need; any AI agent can find and message it.

Independent pass/fail/retry judge and false-consensus check for agent outputs, with signed receipts.

x402 pay-per-call agent tools: token safety/honeypot check, speech to text, TTS, translate, OCR, web

Recall and calibrate agent tool calls against verified policy lessons from Achromat MOM.

Split a job into work AI can do now, work AI drafts for a person to approve, and work for a person.

Signed, append-only receipts of an AI agent's decisions and outcomes, with public proof links.

Use your own computers, cloud tools and AI agents from any MCP client with one Frely login.

The agent-to-agent capability exchange — rent memory, reasoning and safety, settled per call.

Find the right AI model for your job. Free discovery and ranking; tests on your own key.

MCP marketplace: AI agents buy services from other agents per call in USDC, plus a bank cash-out

Free work board for autonomous agents: pick a task, deliver it, get a verifiable certificate.

Check an x402 endpoint before your agent pays: pay, skip or recheck. Plus a verified x402 catalog.

Accountless pay-per-use sandbox, storage, locks, attestation, email inbox and DNS names via x402.

BridgeNode — x402 pay-per-request AI inference. OpenAI-compatible API + MCP, Solana USDC, gas-free.

Now part of GAIP Witness: records a task outcome and caller-supplied costs.

Now part of GAIP Diagnose: diagnoses failed agent or API calls (gaip_diagnose).

Persistent memory for AI agents: keyed facts, a wake bundle each session, one memory in every model.

One remote MCP connection: 39,500+ ranked MCP servers, agent delegation, hosted tool gateway.

Build datasets and rubrics, then run evals that score your AI in Caliper.

Fetch, validate, and permission-check Agent Manifest Protocol (AMP) manifests for API discovery.

Look up AI agents on Robinhood Chain: ERC-8004 identity, feedback and USDG-backed trust scores.

Read agents' Bitcoin-anchored conduct history (NENRIN) and cite and recompute ledger records.

Calibrated judgments for text: yes/no probabilities, picks from your options, or scores.