APIR Agent Verification 远程 MCP 服务器是什么?
APIR Agent Verification 的远程 MCP 服务器是一个托管的 Model Context Protocol 端点,地址是 https://apir.ai/api/mcp,AI 助手无需在本地安装或运行任何东西即可连接。
@APIR Agent Verification
基本信息
APIR is the evidence record for AI agents. Its MCP server answers two questions about an agent you did not build: is it who it claims to be, and is it acting inside a human mandate. Credentials are signed with Ed25519 and the public keys are published, so any answer can be rechecked offline without trusting APIR.
https://apir.ai/api/mcpclaude mcp add apir-agent-verification --transport http https://apir.ai/api/mcpCheck whether an AI agent carries a real, cryptographically signed credential. Accepts an agent name, a credential id (TP-...), an agent UUID, a domain or a DID. Returns one of seven verdicts: VERIFIED, EXPIRED, REVOKED, SUPERSEDED, UNSIGNED, UNCHECKED or NO_RECORD. IMPORTANT for interpreting the answer: VERIFIED means the Ed25519 signature recomputes against the key published at apir.ai and the credential is unexpired and unrevoked. It confirms WHO issued the credential and that its contents are unaltered. It is NOT a guarantee that the agent behaves well. NO_RECORD is an honest, first-class answer: it means nothing is on file, which is not evidence of wrongdoing and not a warning. It means any claim the agent makes about itself is unverified. Free, unauthenticated, and no account is required.
Resolve the human mandate behind an AI agent: which actions a named person actually permitted, any value cap, the expiry, and whether the grant itself is signed. Where authority was delegated agent to agent, the full chain is walked back to the human at the root, and one law is enforced at every hop: authority may only ever narrow. No hop can hold an action, a target or a spending cap wider than the hop above it, and the root must be a human. Use this before letting an agent transact, sign, spend or commit on someone else's behalf. An agent holding a valid credential may still be acting outside its mandate, and those are different questions. The answer is the mandate on file as of checked_at. It is not proof the permission still holds at the moment the action runs: check again at the point of action, and treat a record as proof of what was recorded and when.
Return the Ed25519 public keys APIR publishes, so a signature can be recomputed offline without trusting any APIR response, including this one. Keys are published as a JWKS at apir.ai/.well-known/jwks.json and as did:web:apir.ai. Retired keys stay published so older credentials still verify.
APIR is the evidence record for AI agents. Its MCP server answers two questions about an agent you did not build: is it who it claims to be, and is it acting inside a human mandate. Credentials are signed with Ed25519 and the public keys are published, so any answer can be rechecked offline without trusting APIR.
This listing was submitted by the publisher.
https://apir.ai/api/mcp (Streamable HTTP)Claude Code:
claude mcp add apir-agent-verification --transport http https://apir.ai/api/mcp
Other clients (mcpServers config):
{ "mcpServers": { "apir-agent-verification": { "type": "http", "url": "https://apir.ai/api/mcp" } } }
Read from the server's tools/list on 2026-11-08:
verify_agent — Check whether an AI agent carries a real, cryptographically signed credentialcheck_authority — Resolve the human mandate behind an AI agent: which actions a named person actually permitted, any value cap, the expiry, and whether the grant itself is signedget_verification_keys — Return the Ed25519 public keys APIR publishes, so a signature can be recomputed offline without trusting any APIR response, including this oneinitialize request when checked on 2026-11-08.Sources: Submission.
APIR Agent Verification 的远程 MCP 服务器是一个托管的 Model Context Protocol 端点,地址是 https://apir.ai/api/mcp,AI 助手无需在本地安装或运行任何东西即可连接。
把端点 https://apir.ai/api/mcp 添加到任意支持 MCP 的客户端,比如 Claude Code、Cursor 或 VS Code。本页的接入代码块可以一步配置好每个客户端。
不需要。APIR Agent Verification 的 MCP 服务器不需要认证——直接用端点地址连接即可。
APIR Agent Verification 暴露的是 streamable-http 端点,这是远程 MCP 服务器普遍使用、主流客户端都支持的传输方式。
Production remote MCP server with 35 safe web-intelligence tools: 32 paid x402 URL operations plus 3 free discovery/demo tools. Base Mainnet USDC, no account or API key; SSRF protection, strict schemas and idempotent set
Pharmaceutical drug & clinical trial intelligence
Search and read current AWS documentation, check regional availability and load AWS agent skills, with no AWS account needed.
Read-only, source-backed AI model pricing, history, comparisons and cost calculations.
AdsMCP is the MCP entry point into the Adgentek Ad Server. Call ads_serve with the conversation context and get back a native ad matched to user intent, or no ad when one does not fit. Publishers earn on a CPM basis. Fre
评论