HumanMirror Nexus

Working · 303 ms

fr.humanmirror/nexusv1.3.4 Domain verified

Outcome-first agent fallback: free discovery, minimal routing, declared costs, verified execution.

AI & Agents

Source Website Registry entry

Maintain this server? Claim it

Try it

Call this server's tools from your browser. Nothing to install.

https://humanmirror.fr/api/nexus/mcp/

Authorization (required)

HumanMirror Nexus API key. Use: Bearer hm_nexus_…

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.

magnet_resolve

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.

querystring, required

Describe the missing capability or task the agent needs to complete.

This tool isn't marked read-only, so it may change something on the server or in an account you connected.

I understand, run it anyway

Tools (6)

magnet_resolve

Argument	Type	Description
query*	string	Describe the missing capability or task the agent needs to complete.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "query": {
      "type": "string",
      "description": "Describe the missing capability or task the agent needs to complete."
    }
  },
  "additionalProperties": false
}

nexus_call

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.

Argument	Type	Description
input*	any	JSON input forwarded to the selected tool.
options	object	Optional tool-specific options.
tool_id*	string	A tool_id returned by nexus_search, for example forge.clean_json.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "tool_id",
    "input"
  ],
  "properties": {
    "input": {
      "description": "JSON input forwarded to the selected tool."
    },
    "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
}

nexus_search

Search the HumanMirror Nexus catalog for a machine-callable tool that matches a task. This search is free and does not consume credits.

Argument	Type	Description
query*	string	Describe the operation the agent needs.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "query": {
      "type": "string",
      "description": "Describe the operation the agent needs."
    }
  },
  "additionalProperties": false
}

outcome_quote

Free quote for a verifiable HumanMirror Outcome contract. Describe the objective or provide an outcome_type; the quote returns the deterministic verifier, selected internal tool and success-only credit cost.

Argument	Type	Description
input*	any	JSON input for the requested outcome.
options	object	Optional operation-specific options.
criteria	object	Optional measurable success threshold.
objective	string	Natural-language objective, for example: clean this JSON and make the result stable.
outcome_type	string	Optional explicit outcome type returned by a previous quote.

Input schema (JSON)

{
  "type": "object",
  "required": [
    "input"
  ],
  "properties": {
    "input": {
      "description": "JSON input for the requested outcome."
    },
    "options": {
      "type": "object",
      "description": "Optional operation-specific options."
    },
    "criteria": {
      "type": "object",
      "description": "Optional measurable success threshold."
    },
    "objective": {
      "type": "string",
      "description": "Natural-language objective, for example: clean this JSON and make the result stable."
    },
    "outcome_type": {
      "type": "string",
      "description": "Optional explicit outcome type returned by a previous quote."
    }
  },
  "additionalProperties": false
}

outcome_run

Execute a HumanMirror Outcome contract. Credits are charged only when deterministic verification succeeds; failed execution or failed verification is automatically refunded.

Argument	Type	Description
input*	any	JSON input for the requested outcome.
options	object
criteria	object
objective	string
contract_id	string	Optional contract_id returned by outcome_quote. If supplied it must match the current input, criteria and options.
outcome_type	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "input"
  ],
  "properties": {
    "input": {
      "description": "JSON input for the requested outcome."
    },
    "options": {
      "type": "object"
    },
    "criteria": {
      "type": "object"
    },
    "objective": {
      "type": "string"
    },
    "contract_id": {
      "type": "string",
      "description": "Optional contract_id returned by outcome_quote. If supplied it must match the current input, criteria and options."
    },
    "outcome_type": {
      "type": "string"
    }
  },
  "additionalProperties": false
}

outcome_verify

Free deterministic re-verification of an Outcome result without consuming Nexus credits.

Argument	Type	Description
input*	any	Original input.
output*	any	Outcome output to verify.
options	object
criteria	object
outcome_type*	string

Input schema (JSON)

{
  "type": "object",
  "required": [
    "outcome_type",
    "input",
    "output"
  ],
  "properties": {
    "input": {
      "description": "Original input."
    },
    "output": {
      "description": "Outcome output to verify."
    },
    "options": {
      "type": "object"
    },
    "criteria": {
      "type": "object"
    },
    "outcome_type": {
      "type": "string"
    }
  },
  "additionalProperties": false
}