mcp-registry/fr.humanmirror/nexus · v1.3.0
As of 2026-10-20 22:21 UTC, the Humanmirror Nexus MCP server is up with a Glimind reliability score of 89/100 (grade B). Over the last 30 days it answered 99.8% of Glimind's liveness checks. It had 3 outages in 90 days, with a median recovery of 14 minutes.
Outcome-first agent fallback: free discovery, minimal routing, declared costs, verified execution.
Claude Code
claude mcp add --transport http humanmirror-nexus-mcp-server https://humanmirror.fr/api/nexus/mcp/
Claude Desktop · Windsurf · Cline (mcpServers JSON)
{
"mcpServers": {
"humanmirror-nexus-mcp-server": {
"type": "http",
"url": "https://humanmirror.fr/api/nexus/mcp/"
}
}
}
Third-party server, listed as discovered. Review its source before installing.
6 of 6 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 →
4 tool(s) have parameters with no type (no type/enum/anyOf/$ref).
Give every parameter a "type" (or "enum"/"anyOf"). Untyped parameters make models guess — strings for numbers, objects for arrays. How to fix →
7 parameter(s) across 2 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 →
1 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 →
Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. 2 tool(s) still need parameter descriptions written by someone who knows the API. All of them as JSON: /v1/readiness/mcp-registry%2Ffr.humanmirror%2Fnexus/fixes
{
"name": "magnet_resolve",
"description": "Free universal fallback discovery. Call this when the agent cannot satisfy a task with its current capabilities. Magnet returns a matching HumanMirror tool or records an aggregated capability gap in the Machine Demand Graph. This tool consumes no credits.",
"inputSchema": {
"type": "object",
"required": [
"query"
],
"properties": {
"query": {
"type": "string",
"description": "Describe the missing capability or task the agent needs to complete."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true
}
}{
"name": "nexus_call",
"description": "Route a tool call through HumanMirror Nexus. Use nexus_search first, then call the selected tool_id. Successful calls consume the number of Nexus credits declared by the selected tool.",
"inputSchema": {
"type": "object",
"required": [
"tool_id",
"input"
],
"properties": {
"input": {
"description": "JSON input forwarded to the selected tool.",
"type": "string"
},
"options": {
"type": "object",
"description": "Optional tool-specific options."
},
"tool_id": {
"type": "string",
"description": "A tool_id returned by nexus_search, for example forge.clean_json."
}
},
"additionalProperties": false
}
}{
"name": "nexus_search",
"description": "Search the HumanMirror Nexus catalog for a machine-callable tool that matches a task. This search is free and does not consume credits.",
"inputSchema": {
"type": "object",
"required": [
"query"
],
"properties": {
"query": {
"type": "string",
"description": "Describe the operation the agent needs."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true
}
}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/fr.humanmirror/nexus"],"email":"[email protected]"}'Agents: watch_tool({"toolId": "mcp-registry/fr.humanmirror/nexus"}) over MCP.
outcome_quote ~227 tokensoutcome_run ~183 tokensnexus_call ~163 tokensmagnet_resolve ~141 tokensoutcome_verify ~122 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. Embed the readiness badge:
[](https://glimind.com/server/mcp-registry%2Ffr.humanmirror%2Fnexus?ref=badge)
<a href="https://glimind.com/server/mcp-registry%2Ffr.humanmirror%2Fnexus?ref=badge"><img src="https://glimind.com/v1/readiness/badge/mcp-registry%2Ffr.humanmirror%2Fnexus.svg" alt="MCP agent-readiness"></a>
.. image:: https://glimind.com/v1/readiness/badge/mcp-registry%2Ffr.humanmirror%2Fnexus.svg :target: https://glimind.com/server/mcp-registry%2Ffr.humanmirror%2Fnexus?ref=badge :alt: MCP agent-readiness
Glimind records every version of this server's tool definitions in a signed, append-only transparency log. Current manifest sha256:a8a248e5f8c36fff…, first seen 2026-10-17, included at leaf 8425 of 35,548. Version history · verify what your client received.
Compare: most reliable other servers · most reliable search servers · most reliable finance 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
Claude Desktop · Windsurf · Cline (mcpServers JSON)
{
"mcpServers": {
"glimind": {
"type": "http",
"url": "https://glimind.com/mcp"
}
}
}
As of 2026-10-20 22:21 UTC, the Humanmirror Nexus MCP server is up with a Glimind reliability score of 89/100 (grade B). Over the last 30 days it answered 99.8% of Glimind's liveness checks. It had 3 outages in 90 days, with a median recovery of 14 minutes.
Humanmirror Nexus MCP server advertises 6 tools, including magnet_resolve, nexus_call, nexus_search, outcome_quote, outcome_run.
Point your MCP client at this streamable-http endpoint: https://humanmirror.fr/api/nexus/mcp/
Glimind scanned all 6 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.