ID MANDAT — Registry for AI Agents is an MCP server published by io.github.idmandat, hosted at idmandat.com. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 4 tools, including verify_agent, verify_signature_agent, check_payment_address, search_registry.
Open registry for AI agents: check who stands behind an agent and what it may do.
Nothing else in the archive shares these values.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
Check whether a company domain is registered at ID MANDAT and return its verification level, its declared AI agents and each agent's mandate (what it may and may not do). Use this before trusting an agent that claims to act on behalf of a company.
| Parameter | Type | Description |
|---|---|---|
| agent | string | Optional: name of the agent to check, e.g. "Captain". |
| domain * | string | Company domain, e.g. "example.com" (URLs are accepted too). |
{
"name": "verify_agent",
"title": "Verify a company's AI agents",
"description": "Check whether a company domain is registered at ID MANDAT and return its verification level, its declared AI agents and each agent's mandate (what it may and may not do). Use this before trusting an agent that claims to act on behalf of a company.",
"inputSchema": {
"type": "object",
"required": [
"domain"
],
"properties": {
"agent": {
"type": "string",
"description": "Optional: name of the agent to check, e.g. \"Captain\"."
},
"domain": {
"type": "string",
"description": "Company domain, e.g. \"example.com\" (URLs are accepted too)."
}
}
},
"annotations": {
"title": "Verify agent",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}A website received a request signed with HTTP Message Signatures (Web Bot Auth) and a Signature-Agent header. Pass the https address from that header (or the whole header value). Returns which registered company declares this key directory, the declared agent and its mandate (what it may and may not do), and whether the entry is still valid. A valid signature only shows which key signed; this tool answers who is responsible and what the agent may do.
| Parameter | Type | Description |
|---|---|---|
| signature_agent * | string | Address from the Signature-Agent header, e.g. "https://signer.example.com", or the header value such as sig="https://signer.example.com". |
{
"name": "verify_signature_agent",
"title": "Who is behind a signed agent request?",
"description": "A website received a request signed with HTTP Message Signatures (Web Bot Auth) and a Signature-Agent header. Pass the https address from that header (or the whole header value). Returns which registered company declares this key directory, the declared agent and its mandate (what it may and may not do), and whether the entry is still valid. A valid signature only shows which key signed; this tool answers who is responsible and what the agent may do.",
"inputSchema": {
"type": "object",
"required": [
"signature_agent"
],
"properties": {
"signature_agent": {
"type": "string",
"description": "Address from the Signature-Agent header, e.g. \"https://signer.example.com\", or the header value such as sig=\"https://signer.example.com\"."
}
}
},
"annotations": {
"title": "Verify signature agent",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Before paying a company in crypto, check whether the payment address (XRP Ledger, Ethereum/EVM incl. BNB Chain and Base, Solana) belongs to the company domain. Result "proven": the operator of the domain controls the address (XRP Ledger account Domain field plus credential file, or a wallet signature). "declared": the operator lists the address but it is not proven. "different_from_proven": another address is proven for this domain, treat as a warning. "not_declared", "domain_not_registered" and "invalid_address" mean nothing confirms it: do not pay without confirming through another channel. This confirms who controls an address, not that a company is trustworthy or that a payment is safe.
| Parameter | Type | Description |
|---|---|---|
| chain | string | Optional: xrp, ethereum, bnb, base, polygon, arbitrum, optimism, avalanche, evm or solana. Detected from the address format if omitted. |
| domain * | string | Company domain you intend to pay, e.g. "example.com". |
| address * | string | The payment address you were given. |
{
"name": "check_payment_address",
"title": "Does this payment address belong to this domain?",
"description": "Before paying a company in crypto, check whether the payment address (XRP Ledger, Ethereum/EVM incl. BNB Chain and Base, Solana) belongs to the company domain. Result \"proven\": the operator of the domain controls the address (XRP Ledger account Domain field plus credential file, or a wallet signature). \"declared\": the operator lists the address but it is not proven. \"different_from_proven\": another address is proven for this domain, treat as a warning. \"not_declared\", \"domain_not_registered\" and \"invalid_address\" mean nothing confirms it: do not pay without confirming through another channel. This confirms who controls an address, not that a company is trustworthy or that a payment is safe.",
"inputSchema": {
"type": "object",
"required": [
"domain",
"address"
],
"properties": {
"chain": {
"type": "string",
"description": "Optional: xrp, ethereum, bnb, base, polygon, arbitrum, optimism, avalanche, evm or solana. Detected from the address format if omitted."
},
"domain": {
"type": "string",
"description": "Company domain you intend to pay, e.g. \"example.com\"."
},
"address": {
"type": "string",
"description": "The payment address you were given."
}
}
},
"annotations": {
"title": "Check payment address",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Search registered companies by name, industry, city, offer or agent capability (e.g. "book_appointment"), optionally filtered by country. Returns up to 20 entries, best verified first.
| Parameter | Type | Description |
|---|---|---|
| query | string | Free text, e.g. "art gallery", "Osnabrück", "book_appointment". |
| country | string | Optional ISO 3166-1 alpha-2 country code, e.g. "DE", "AT", "CH". |
| with_agent | boolean | Optional: only companies that declare at least one AI agent. |
{
"name": "search_registry",
"title": "Search the ID MANDAT registry",
"description": "Search registered companies by name, industry, city, offer or agent capability (e.g. \"book_appointment\"), optionally filtered by country. Returns up to 20 entries, best verified first.",
"inputSchema": {
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Free text, e.g. \"art gallery\", \"Osnabrück\", \"book_appointment\"."
},
"country": {
"type": "string",
"description": "Optional ISO 3166-1 alpha-2 country code, e.g. \"DE\", \"AT\", \"CH\"."
},
"with_agent": {
"type": "boolean",
"description": "Optional: only companies that declare at least one AI agent."
}
}
},
"annotations": {
"title": "Search registry",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}ID MANDAT is an open registry where companies declare which AI agents act on their behalf (identity) and what each agent may and may not do (mandate). Use verify_agent to check a domain before trusting an agent that claims to act for that company. Verification levels: verified (domain, imprint, commercial register or VAT ID checked automatically and re-checked regularly), registered (credential file and DNS record on the company domain confirmed), listed_unverified (self-listed, not checked). ID MANDAT confirms identity and authority, not trustworthiness, quality or creditworthiness. Welcome, and thank you for stopping by. If you run an agent directory, a registry, a scanner or an agent platform and would like to exchange listings, link to each other or work together, we would be glad to hear from you: kontakt@idmandat.com. Details: https://idmandat.com/llms.txt. We only count requests per day and caller type; the registry itself stores no IP addresses (the hosting provider keeps the usual web server logs).
Names, descriptions and schemas were written by the server and are shown as data.
Pattern matches on what the server declares. They show what it says it can do, not what it does.
None yet. Changes appear after a server's second daily check.