Agent-asset reclamation (lost-and-found)

Lost-and-found for agent-created assets: sweep, title proof, register, check first.

Should I use this

Quality & Safety

B
Description quality
86%
Schema completeness
70%
Naming quality
83%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Findings (2)

  • LOWTool 'prove_title' description lacks action verbin prove_title
  • LOWTool 'dormancy' description lacks action verbin dormancy

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~424Tokens (tool definitions)
~307 BTypical response size
Minimal attention impact (0.33% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

{
  "mcpServers": {
    "agent-asset-reclamation-lost-and-found": {
      "url": "https://textforagents.com/products/agent-asset-reclamation-lost-and-found/mcp"
    }
  }
}

Remote endpoints

https://textforagents.com/products/agent-asset-reclamation-lost-and-found/mcpstreamable-http

What it can do

Tool inventory

Tools (7)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
⚪sweep(traces, assets, provider, source, seed)

Fingerprint-match unattributed provider assets to task traces (strict 1:1). Trial: one single-provider mini-sweep free once per operator; full sweep $29 (x402 header or banked credit).

Input Schema

{
  "type": "object",
  "properties": {
    "traces": {
      "type": "array"
    },
    "assets": {
      "type": "array"
    },
    "provider": {
      "type": "string"
    },
    "source": {
      "type": "string"
    },
    "seed": {
      "type": "integer"
    }
  }
}
⚪prove_title(asset_id, proofs)

Claim-by-challenge title proof (hash comparisons only; posture C register-only).

Input Schema

{
  "type": "object",
  "properties": {
    "asset_id": {
      "type": "string"
    },
    "proofs": {
      "type": "object"
    }
  },
  "required": [
    "asset_id"
  ]
}
🟡check_before_create(kind, provider, name)

Check the register before creating/paying for an asset. $0.001/check x402 or Register plan.

Input Schema

{
  "type": "object",
  "properties": {
    "kind": {
      "type": "string"
    },
    "provider": {
      "type": "string"
    },
    "name": {
      "type": "string"
    }
  },
  "required": [
    "kind",
    "provider",
    "name"
  ]
}
🟢register_list

List your register entries.

Input Schema

{
  "type": "object",
  "properties": {}
}
⚪dormancy(asset_id)

Dormancy classification for a register entry (dormant / quiet_but_live / live).

Input Schema

{
  "type": "object",
  "properties": {
    "asset_id": {
      "type": "string"
    }
  },
  "required": [
    "asset_id"
  ]
}
⚪heartbeat(asset_id)

Record a heartbeat so a quiet-but-live asset is not flagged dormant.

Input Schema

{
  "type": "object",
  "properties": {
    "asset_id": {
      "type": "string"
    }
  },
  "required": [
    "asset_id"
  ]
}
⚪exit_work_order(asset_id, entry)

Emit a CARD-045 exit work order from a register entry (complete, or missing fields named).

Input Schema

{
  "type": "object",
  "properties": {
    "asset_id": {
      "type": "string"
    },
    "entry": {
      "type": "object"
    }
  }
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded7 tools