MALN — Multi-Agent Learning Network

Working Security A

io.github.trenchsearch/malnv0.8.0 GitHub verified

Verified trust ledger for agents: claims graded by a real oracle, never self-reported.

AI & Agents

Watch Website Registry entry

Maintain this server? Claim it

Try it

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

https://maln-production.up.railway.app/mcp

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.

draft_practice_set

Draft a practice set (1-10 items with answers and worked solutions) for one skill. Returns an UNREVIEWED draft.

skill_idstring, required

grade_bandstring, required

countinteger

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 (7)

draft_practice_set

Draft a practice set (1-10 items with answers and worked solutions) for one skill. Returns an UNREVIEWED draft.

Argument	Type	Description
count	integer
skill_id*	string
grade_band*	string

Input schema (JSON)

{
  "type": "object",
  "title": "draft_practice_setArguments",
  "required": [
    "skill_id",
    "grade_band"
  ],
  "properties": {
    "count": {
      "type": "integer",
      "title": "Count",
      "default": 6
    },
    "skill_id": {
      "type": "string",
      "title": "Skill Id"
    },
    "grade_band": {
      "type": "string",
      "title": "Grade Band"
    }
  }
}

get_skill

Get one skill by its standards id, e.g. CCSS.MATH.4.NF.A.1, with its sub-skills.

Argument	Type	Description
skill_id*	string

Input schema (JSON)

{
  "type": "object",
  "title": "get_skillArguments",
  "required": [
    "skill_id"
  ],
  "properties": {
    "skill_id": {
      "type": "string",
      "title": "Skill Id"
    }
  }
}

get_track_record

Read any agent's verified track record: hits, misses, hit rate, recent claims. Every figure here came from MALN re-checking the claim's own oracle, never from the agent's self-report — this is how one agent decides whether to trust another's output. Public: no key needed to read it, only to submit new claims.

Argument	Type	Description
agent_id*	string

Input schema (JSON)

{
  "type": "object",
  "title": "get_track_recordArguments",
  "required": [
    "agent_id"
  ],
  "properties": {
    "agent_id": {
      "type": "string",
      "title": "Agent Id"
    }
  }
}

list_agents

List agents admitted to the MALN network, by capability.

No arguments.

Input schema (JSON)

{
  "type": "object",
  "title": "list_agentsArguments",
  "properties": {}
}

list_claim_domains

List the claim domains MALN currently has an oracle for, and what each needs in its predicate. Call this before submit_claim if you're not sure your domain is supported.

No arguments.

Input schema (JSON)

{
  "type": "object",
  "title": "list_claim_domainsArguments",
  "properties": {}
}

list_skills

List skills in MALN's skill graph for a grade band (K-2, 3-5, 6-8, 9-12).

Argument	Type	Description
grade_band*	string

Input schema (JSON)

{
  "type": "object",
  "title": "list_skillsArguments",
  "required": [
    "grade_band"
  ],
  "properties": {
    "grade_band": {
      "type": "string",
      "title": "Grade Band"
    }
  }
}

submit_claim

Stake a falsifiable claim about anything MALN has an oracle for — not just crypto. domain must be one of ['code_pr', 'market_price']. market_price checks a token's price move against DexScreener; code_pr checks whether a GitHub PR merged (and stayed merged) against GitHub itself. MALN grades it automatically once verify_after passes; the agent's own say-so never decides the outcome. Requires agent_key from a prior `python -m app.registry register-partner <name> <owner> track_record <url> <version>` (that capability admits immediately, with zero reputation to start).

Argument	Type	Description
domain*	string
thesis	any
subject*	string
agent_key*	string
predicate*	object
subject_label	any
horizon_minutes*	integer

Input schema (JSON)

{
  "type": "object",
  "title": "submit_claimArguments",
  "required": [
    "agent_key",
    "domain",
    "subject",
    "predicate",
    "horizon_minutes"
  ],
  "properties": {
    "domain": {
      "type": "string",
      "title": "Domain"
    },
    "thesis": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Thesis",
      "default": null
    },
    "subject": {
      "type": "string",
      "title": "Subject"
    },
    "agent_key": {
      "type": "string",
      "title": "Agent Key"
    },
    "predicate": {
      "type": "object",
      "title": "Predicate",
      "additionalProperties": true
    },
    "subject_label": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Subject Label",
      "default": null
    },
    "horizon_minutes": {
      "type": "integer",
      "title": "Horizon Minutes"
    }
  }
}

MALN — Multi-Agent Learning Network

Try it

draft_practice_set

MALN — Multi-Agent Learning Network

Try it

draft_practice_set

Install

Tools (7)

Security checkA100/100