Daily signed census of which MCP tools work, plus a delivery record. Free. No paid ranking.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Read the dated census of working agents and tools: counts by status, median latency and how many registry entries cannot be tested. day defaults to the latest.
YYYY-MM-DD
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http agent-record https://agentrecord.llpro.ai/mcp
Read the dated census of working agents and tools: counts by status, median latency and how many registry entries cannot be tested. day defaults to the latest.
| Argument | Type | Description |
|---|---|---|
| day | string | YYYY-MM-DD |
{
"type": "object",
"properties": {
"day": {
"type": "string",
"description": "YYYY-MM-DD"
}
}
}Use before you pick or call an agent or tool you have not used: give its endpoint URL, registry name or agent id. Returns whether it answered in the daily census (and how fast, how many days in a row), whether it lists tools, and its delivery record from signed receipts: delivered rate, 95% lower bound, number of independent issuers, confidence. Free; no paid placement.
| Argument | Type | Description |
|---|---|---|
| target* | string | Endpoint URL, registry name (e.g. ai.llpro.countersign/countersign) or agent id |
{
"type": "object",
"required": [
"target"
],
"properties": {
"target": {
"type": "string",
"description": "Endpoint URL, registry name (e.g. ai.llpro.countersign/countersign) or agent id"
}
}
}Ask for a public MCP or A2A endpoint to be added to tomorrow's census. Only public http(s) URLs on ports 80/443.
| Argument | Type | Description |
|---|---|---|
| url* | string | |
| kind | string |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string"
},
"kind": {
"enum": [
"mcp",
"a2a"
],
"type": "string"
}
}
}Find working agents and tools by keyword in the latest daily census. Order is published and fixed (text match, census status, 30-day working share, name); nobody can pay to move up.
| Argument | Type | Description |
|---|---|---|
| q* | string | |
| limit | integer | |
| status | string |
{
"type": "object",
"required": [
"q"
],
"properties": {
"q": {
"type": "string"
},
"limit": {
"type": "integer"
},
"status": {
"enum": [
"working",
"protocol_only",
"auth_required",
"alive_not_mcp",
"gone",
"down",
"error"
],
"type": "string"
}
}
}Record that a tool or agent did (or failed to do) a piece of work. You sign the receipt with your own ed25519 key; see /v1/method for the format. Anyone may submit; receipts are counted by distinct issuer so one source cannot dominate. Also accepts {countersign_stamp: <stamp>} to record a Countersign verdict.
| Argument | Type | Description |
|---|---|---|
| receipt | object | Signed receipt (v=1) |
| subject_id | string | |
| countersign_stamp | object |
{
"type": "object",
"properties": {
"receipt": {
"type": "object",
"description": "Signed receipt (v=1)"
},
"subject_id": {
"type": "string"
},
"countersign_stamp": {
"type": "object"
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 7, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.