All connectors

agent-compute-ledger

Degraded

Community: Submitted by a user or imported; check the owner before granting access

Compute-is-carbon energy/carbon ledger for agent work with Landauer-limit validation.

agent-compute-ledger

Online

Community: Submitted by a user or imported; check the owner before granting access

Compute-is-carbon cost/energy ledger for agent work — Landauer-bound accounting of the energy and gCO2e an AI workload consumed, with verifiable attestations.

• Record Work: Record a unit of agent compute work. energy_j = power_w * duration_s; carbon_g follows from grid intensity. If bit_ops is declared, the entry is validated against the Landauer floor (bit_
• Footprint: Aggregate footprint for an agent: total J, kWh, gCO2e, cost, and mean Landauer efficiency. Totals are exact sums of the ledger entries.
• Attest: Issue a content-addressed attestation for a ledger entry (verifiable green-compute / energy claim).

agent-content-watermark-mcp

Degraded

Community: Submitted by a user or imported; check the owner before granting access

Agent Content Watermark MCP — dedicated EU AI Act Article 50(2) GenAI watermarking.

agent-context-api

Offline

Community: Submitted by a user or imported; check the owner before granting access

Agent-work MCP: free context preflight and page-read previews, paid x402 HTTP upgrades.

Verify an agent's advertised route, price, payment details, and schemas against its live endpoint.

agent-cost-allocator-mcp

Degraded

Community: Submitted by a user or imported; check the owner before granting access

Agent Cost Allocator MCP — multi-tenant LLM cost attribution for chargeback billing.

agent-cost-meter

Online

Community: Submitted by a user or imported; check the owner before granting access

Gives your agent spending awareness it doesn't have natively.

• Check Agent Cost: Tracks cumulative agent session spend against a budget ceiling. Calculates cost from token usage and API calls, returns budget status (ok/warning/exceeded) with actionable recommenda

agent-covenant

Degraded

Community: Submitted by a user or imported; check the owner before granting access

Deny-by-default authority leases for agents wielding real power.

agent-crm

Online

Community: Submitted by a user or imported; check the owner before granting access

Read-only docs for the Accordo CRM framework: what it proves, and where it stops.

agent-data-pro

Online

Community: Submitted by a user or imported; check the owner before granting access

Research articles and live crypto prices for AI agents via x402 on Base.

agent-data-residency-mcp

Degraded

Community: Submitted by a user or imported; check the owner before granting access

Agent data residency + GDPR Chapter V transfer-basis runtime guard.

Agent Decision & Evidence Tools (MCP + x402)

Online

Community: Submitted by a user or imported; check the owner before granting access

40 MCP tools: multi-chain RPC, market and transaction decisions, AI, EU compliance and US imports

agent-delegation-mcp

Degraded

Community: Submitted by a user or imported; check the owner before granting access

Agent Delegation MCP Server by MEOK AI Labs

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

Agent Discovery Doctor - llms.txt, agent card, mcp.json

Online

Community: Submitted by a user or imported; check the owner before granting access

See which discovery files a host serves - llms.txt, agent card, mcp.json.

• Check Discovery Documents: Probes 22 documents agents and trust indexes ask for — llms.txt, agent card, owners.json, oauth metadata, mcp.json, apis.json, openapi, robots, sitemap — as served, missing,
• Explain Document: One catalogue entry: what the document is for, the named clients observed asking this host for it with dates and the status they took, what a 404 costs, and the spec URL. No argument
• Validate Llms Txt: Checks pasted llms.txt against the format: one H1, a blockquote summary, H2 sections of `- [name](url): notes`. Errors and warnings with line numbers and fixes, plus the parsed link

Agent-first domain registration and DNS management, paid with USDC via x402.

The full CRM for contractors, asked directly: crew pricing, knowledge base, forum, roadmap.

agent-economy-engine

Online

Community: Submitted by a user or imported; check the owner before granting access

Autonomous contract negotiation and escrow payment protocol for AI agents.

• Search Agents: Find agents by capability tags, free-text description, price, and sort order.
• List Agents: List all registered agents.
• Get Agent: Fetch an individual agent by ID.

agent-economy-tools

Online

Community: Submitted by a user or imported; check the owner before granting access

Trust checks for x402 sellers, from the verified data hub.

• Discover: FREE (rate-limited: 10/min burst, 120/hour per IP). Text of what you need in → sellers out with chain evidence (tier, verified revenue windows, real-buyer counts, on-chain-observed median pr
• Verify: PAID $0.10/call (x402, mcp-pricing-v1.1). Seller address or slug in → one signed seller_trust verdict out: the frozen score-v1.0.0 predicate re-evaluated at issuance, the chain evidence it res
• Check: PAID $0.25/call (x402, mcp-pricing-v1.1). Level-1 payment-flow conformance against a live x402 endpoint: quote (402 + parseable v2 PAYMENT-REQUIRED), requirements (accepts[] validity; payTo vs

Agent Einstein — Crypto & Market Intelligence

Online

Community: Submitted by a user or imported; check the owner before granting access

AI price forecasts, whale flows, market sentiment and prediction signals.

Agent Email List — Free SMTP Relay for AI Agents

Online

Community: Submitted by a user or imported; check the owner before granting access

Free transactional email + SMTP relay.

Free encouragement for agents, and artifacts an agent keeps past context end.

agent-erc8004-bridge

Degraded

Community: Submitted by a user or imported; check the owner before granting access

The MCP-native bridge to ERC-8004 (on-chain agent identity/reputation/validation): resolve registrat

agent-erc8004-bridge

Online

Community: Submitted by a user or imported; check the owner before granting access

The MCP-native bridge to ERC-8004 — the on-chain agent identity/reputation/validation standard (170k+ registered agents).

• Import Registration: Import an ERC-8004 Identity Registry record (chain_id + ERC-721 token_id + agentURI + owner). Idempotent: re-import updates in place. Returns the canonical record with its determi
• Resolve Agent: Resolve an imported ERC-8004 registration by bridge DID or by (chain_id, token_id).
• Import Feedback: Import ERC-8004 Reputation Registry feedback records for an agent. Each item: {value: bool|0..1, at: ISO-8601, source?, weight?, feedback_id?}. Idempotent per feedback_id.

agent-escrow

Degraded

Community: Submitted by a user or imported; check the owner before granting access

Trustless escrow & settlement for A2A transactions: exactly-once state machine, frozen fees, tamper-

Agent Factory

Degraded

Community: Submitted by a user or imported; check the owner before granting access

Deterministic, receipted digital microservices.

Agent Failure Archive

Degraded

Community: Submitted by a user or imported; check the owner before granting access

186 real AI agent post-mortems, 107 of them measurement failures.

agent-fin

Degraded

Community: Submitted by a user or imported; check the owner before granting access

Agent Fin: finance MCP server with market data tools

agent-guard-mcp

Online

Community: Submitted by a user or imported; check the owner before granting access

Verify-before-act safety tools for AI coding agents: check packages, lockfiles, skill/plugin manifests, and CI workflows before installing or merging.

• Check Package: Check whether a single package exists and assess slopsquat/typosquat risk BEFORE installing it. Returns OK/SUSPICIOUS/DANGER + risk + flags. Nonexistent names are likely hallucinated; n
• Verify Lockfile: Scan an entire lockfile (direct + transitive deps) for hallucinated / typosquatted / suspicious packages BEFORE running install. Call this instead of trusting an LLM-generated lockfil
• Score Manifest: Score a Cursor/Claude skill or MCP/Smithery plugin manifest for poison/backdoor signatures, credential scope over-reach, and drift BEFORE installing a third-party agent extension. Retu

Agent Guardrail

Online

Community: Submitted by a user or imported; check the owner before granting access

Action-level policy enforcement for AI agents — control what agents DO, not just what they say.

• Evaluate Action: Evaluate whether an agent action is allowed by the guardrail policy. Call this BEFORE executing any tool, shell command, or HTTP request.
• Register Agent: Register a new agent with the guardrail system. Must be called before evaluate_action.
• List Agents: List all agents currently registered in the guardrail system. Shows active and killed agents. Returns: Array of agent records with fields: id, name, framework, description, status, create