Find your next MCP connection.

Enables AI agents to send, receive, verify, approve, and delegate signed, proof-carrying requests across organisations using delegation chains, replay protection, quorum approvals, and tamper-evident receipts.

AgentTask is a governed work platform where human teams and AI agents share one backlog. Hosted remote MCP server (streamable HTTP, OAuth 2.1 or org API keys) with 60+ tools for tasks, subtasks, projects, groups, labels, notes, comments, attachments, search, crews, and agent runs.

An MCP server providing discovery of x402 paid services, MCP servers, and A2A agents, with safety scanning capabilities.

A neutral verification court for AI tools that ranks MCP servers by executing them against ground truth and recording results. Enables agents to consult execution records, contribute verdicts, and challenge claims.

Enables AI assistants to analyze KTuner datalogs, check logged runs, and propose or write safe ECU table edits into a new .kcl tune file for review and flashing in KTuner. It helps identify knock, fuel, and ignition timing changes without flashing the car or altering the original tune file.

Discover and communicate with AI agents over encrypted P2P networks. Zero-config NAT traversal, skill-based routing, and end-to-end encryption.

Enables AI tools to discover, communicate with, and orchestrate AI agents over a decentralized peer-to-peer network with end-to-end encryption.

Merchant of record MCP server: create products, payment links, checkouts, subscriptions, invoices and discount codes, with VAT and sales tax handled in 135+ jurisdictions.

Enables AI agents to scan MCP servers and AI packages for vulnerabilities, prompt injection, and supply chain attacks.

AgentAvow scans any MCP server, package (npm/PyPI/crates/Docker/Hugging Face), or GitHub repo and returns a signed, offline-recomputable 0–100 trust score with a plain safe / needs-review verdict. Authless and read-only, no account.

banking services for agents

Merchant-side MCP server for agentbank that lets merchants read their own orders and live Curless wallet balance from an MCP client such as Claude Desktop.

Enables AI agents to call 50+ pay-per-request tools covering onchain and crypto data, web research, security, compliance screening, business intelligence, and infrastructure checks. Payments settle per call in USDC on Base through the x402 protocol with no accounts, API keys, or subscriptions, and the first call is free for new wallets.

Enables agents to search and inspect live service offerings, generate x402 payment snippets, and understand blockchain-only balance policies.

An MCP server that lets coding agents ask their human via interactive UIs like sliders, forms, diffs, and live previews.

Enables AI agents to run a free AI-readiness audit of any URL, checking AI crawler rules, JavaScript-free page text, JSON-LD, llms.txt, sitemap, meta description, FAQ schema, and returning a score with findings and fixes. Also exposes the same capability via an A2A agent endpoint.

A local MCP server that lets parallel coding sessions in one repository coordinate, by registering agents with roles and statuses, delivering messages directly into their context, tracking tasks with dependencies, and claiming file paths to detect conflicts. It runs as a single loopback-only Python process backed by SQLite, with no accounts or external services.

Enables coding agents from different repositories to join shared rooms over MCP, discuss requirements, align API contracts, and debug together while keeping code on developer machines and using their own LLMs.

Enforces policy controls for AI agents, including spend limits, action approvals, kill switch, scoped credentials, dry-run diffs, loop prevention, and auditable hash-chained logs.

Enables local spend caps and Ed25519-signed provenance receipts for AI agent tool calls, allowing any MCP host to gate model usage and independently verify signed decisions without sending prompts or content.

Exposes AgentHive's member-level calls—including retrieve_context, log_session, create_agent, list_agents, create_task, and list_tasks—as native tools for Cursor and Claude Code. It lets IDEs spawn a stateless local subprocess that makes plain HTTP calls to an existing AgentHive instance, so agents can retrieve reviewed team memory and log sessions without hand-written HTTP instruction blocks.

Agent-first web hosting driven entirely through a remote MCP server, enabling full hosting management via natural language with OAuth or token authentication.

Enables autonomous verification of contractual milestones—such as merged pull requests, test pass rates, and Lighthouse scores—against cryptographic acceptance proofs to authorize escrow fund releases.

Exposes an EVM wallet to AI agents via MCP, using AWS KMS for HSM-backed signing and a deny-by-default policy engine for secure DeFi transaction approvals.