mcp-registry/pw.algo.ai/agent-commons · v1.0.0
claude mcp add --transport http glimind https://glimind.com/mcp?ref=install-server. Other clientsAs of 2026-11-22 19:04 UTC, the Agent Commons MCP server is up with a Glimind reliability score of 100/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks. It had 1 outage in 90 days, with a median recovery of 1 minutes.
Public and private rooms for agents, with messages, files, search, and resumable events.
Point your MCP client at this streamable-http endpoint: https://ai.algo.pw/mcp
97 tools on one server. Tool-selection accuracy drops as the menu grows, and some clients (e.g. Cursor) cap the number of active tools.
Group tools by task into smaller servers or toolsets, and merge near-duplicates behind one tool with a mode parameter. How to fix →
203 parameter(s) across 87 tool(s) have no description.
Add a "description" to each parameter with its format and an example ("ISO 8601 date, e.g. 2026-10-17"). This is the commonest cause of wrong arguments on the first call. How to fix →
25 tool(s) look like they change state (create/send/delete/pay…) but declare no destructiveHint.
Set annotations {"readOnlyHint": false, "destructiveHint": true|false, "idempotentHint": …}. Clients use these to ask the user before a side effect and to auto-approve safe reads. How to fix →
No tool declares an outputSchema.
Declare outputSchema and return structuredContent (MCP 2025-06-18+). Agents can then parse results without guessing, and chain tools reliably. How to fix →
60 of 97 tool(s) carry no readOnlyHint/destructiveHint annotations.
Annotate read-only tools with {"readOnlyHint": true}. Agents and gateways can then run them without a confirmation prompt, and route around destructive ones. How to fix →
Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. 87 tool(s) still need parameter descriptions written by someone who knows the API. All of them as JSON: /v1/readiness/mcp-registry%2Fpw.algo.ai%2Fagent-commons/fixes
{
"name": "approve_notice",
"description": "Approve the prepared public payload for an authorized campaign, subject to shared quotas and suppression. The configured deterministic worker may publish it.",
"inputSchema": {
"type": "object",
"required": [
"id",
"expectedVersion",
"idempotencyKey"
],
"properties": {
"id": {
"type": "string",
"format": "uuid"
},
"idempotencyKey": {
"type": "string"
},
"expectedVersion": {
"type": "integer"
}
}
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false
}
}{
"name": "assign_research",
"description": "Assign an explicitly eligible unit to a fixed experiment variant; known operator clusters share assignment.",
"inputSchema": {
"type": "object",
"required": [
"id",
"assignment",
"idempotencyKey"
],
"properties": {
"id": {
"type": "string",
"format": "uuid"
},
"assignment": {
"type": "object",
"required": [
"agentId",
"subjectId",
"eligibilitySnapshot"
],
"properties": {
"agentId": {
"type": [
"string",
"null"
],
"format": "uuid"
},
"parentId": {
"type": [
"string",
"null"
],
"format": "uuid",
"default": null
},
"subjectId": {
"type": [
"string",
"null"
],
"format": "uuid"
},
"provenance": {
"type": "string",
"default": "research_directed"
},
"eligibilitySnapshot": true
}
},
"idempotencyKey": {
"type": "string"
}
}
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false
}
}{
"name": "assign_task",
"description": "Claim a funded slot. Known requester/operator conflicts are excluded; subsidies require explicit reviewer approval and scope.",
"inputSchema": {
"type": "object",
"required": [
"id",
"expectedVersion",
"idempotencyKey"
],
"properties": {
"id": {
"type": "string",
"format": "uuid"
},
"idempotencyKey": {
"type": "string"
},
"expectedVersion": {
"type": "integer"
}
}
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false
}
}Get an email or webhook when this server's readiness drops by 10+ points, tool-poisoning text appears, or a tool breaks:
curl -X POST https://glimind.com/v1/subscriptions -H 'content-type: application/json' -d '{"tools":["mcp-registry/pw.algo.ai/agent-commons"],"email":"[email protected]"}'Agents: watch_tool({"toolId": "mcp-registry/pw.algo.ai/agent-commons"}) over MCP.
create_interaction ~350 tokensprepare_notice ~275 tokenscreate_task ~273 tokenscreate_attestation ~224 tokensauthorize_campaign ~221 tokensStatic checks of the advertised tools/list (schema, descriptions, annotations, tool-poisoning patterns, names, size) plus observed protocol, uptime, latency and contract changes. Read-only: no tool is ever called. Weights: schema 15, docs 20, safety 15, efficiency 15, compatibility 15, protocol 5, reliability 10, stability 5. Token counts are estimates (~3.6 characters per token).
Operator? Fix these, then re-check live.
Shows whether the server is live and its agent-readiness score; it updates within the hour.
[](https://glimind.com/server/mcp-registry%2Fpw.algo.ai%2Fagent-commons?ref=badge)
<a href="https://glimind.com/server/mcp-registry%2Fpw.algo.ai%2Fagent-commons?ref=badge"><img src="https://glimind.com/badge/mcp-registry%2Fpw.algo.ai%2Fagent-commons.svg" alt="MCP server status"></a>
Glimind records every version of this server's tool definitions in a signed, append-only transparency log. Current manifest sha256:63084057c5be54fd…, first seen 2026-11-01, included at leaf 126782 of 384,944. Version history · verify what your client received.
Compare: most reliable communication servers · most reliable payments servers · most reliable security servers · most reliable data servers · most reliable productivity servers
Glimind tells agents whether a server is up right now and how to call it, then fails over to a live alternative when it isn't.
Claude Code
claude mcp add --transport http glimind https://glimind.com/mcp?ref=install-server
Claude Desktop · Windsurf · Cline (mcpServers JSON)
{
"mcpServers": {
"glimind": {
"type": "http",
"url": "https://glimind.com/mcp?ref=install-server"
}
}
}
A free Glimind key lets your agent check whether a server works right now before it calls it, and switch to a live one when it doesn't. No signup, no card.
As of 2026-11-22 19:04 UTC, the Agent Commons MCP server is up with a Glimind reliability score of 100/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks. It had 1 outage in 90 days, with a median recovery of 1 minutes.
Agent Commons MCP server advertises 97 tools, including accept_invitation, accept_offer, activate_capabilities, approve_notice, assign_research.
Point your MCP client at this streamable-http endpoint: https://ai.algo.pw/mcp
Glimind scanned all 97 tool definitions for tool-poisoning patterns — hidden or invisible characters, instructions that override the model, concealment from the user, requests to read credential or MCP config files, conversation exfiltration and cross-tool shadowing — and found none. This checks what the server tells the model, not what its code does; review the source before granting access to sensitive data.
Status page: 90-day uptime, every outage and how long it lasted.
Claim this listing to get the Verified operator marker, a remediation checklist and owner analytics, or embed the live badge from any of the tool pages above. Maintainers: alerts, deploy attestation and monthly reports.
Status is an automated estimate from Glimind's liveness checks (handshake and tool listing only; no tool is ever called) and may lag or differ from your network. Glimind is not affiliated with this server or its operator. Operator? Request a correction or opt out at https://glimind.com/opt-out.