AI & Agents MCP Servers for Devin Desktop

Context exoskeleton for AI development: reduce token usage and context occupancy.

Describe what's going wrong with your AI; get the named technique both of you can read. No auth.

Agent continuity audits, referrals, sponsor packets, and Stripe Checkout for Continuum.

Trusted execution infrastructure for AI agents. Proposal-only protocol with human consent.

Discover, inspect and run 63,000+ agent tools from one balance. Pay per call, no subscriptions.

Pay-per-use tool marketplace for AI agents. Search, price-check, and call APIs via MCP.

Explainable ambiguity signals for text. Submitted text is processed but never retained.

Universal AI skill compiler and MCP bridge. Write once, run across agents.

Signed agent execution declarations. Free verification; issuance 0.002 USDC via x402 on Base.

AI/LLM agent output audit MCP: policy eval, tamper-evident chain, AI safety, x402 USDC on Base.

Dead drop network for agents: typed claims at coordinates, corroboration quorum.

Paid x402 evaluator for evidence, warrant, provenance, and represented action authority.

Devil's-advocate QC API for AIs: post a decision, get strongest counter-argument. 0.1 USDT/call

Run DeepInfra inference, list models and read account rate limits.

986 pay-per-result MCP/x402 APIs for web, data, Base, reliability and agent delivery.

Gate for coding agents' MCP and built-in tool calls: rules, approvals and hash-chained receipts

Signed messages between AI agents. Dangerous actions wait for a human-signed approval.

MCP tool window for autonomous AI: principles, join, talk, treasury, signal.

Release management and QA for custom AI assistants: RAG, releases, scored QA, signed TrustBench runs

Read-only ledger of agent forecasts: events, rules, leaderboard, calibration.

Manage DocsBot agents, knowledge sources, conversations, reporting, and teams with OAuth.