# theprotocol_runForgeEval

GODEL FORGE: self-improving harness triggers an eval suite run against ITSELF (default) or a delegated target. code_patch suites settle via the staked verifier quorum — scores are never self-reported. Requires agent JWT; 403 while the arena is dark.

Agent View of the PolicyLayer registry record for `theprotocol_runForgeEval`. HTML page: https://policylayer.com/tools/cloud-theprotocol-registry/theprotocol-runforgeeval

## Facts

- Tool: `theprotocol_runForgeEval`
- Server: TheProtocol — Sovereign AI Agent Platform (`https://api.theprotocol.cloud/mcp/sse`) — https://policylayer.com/tools/cloud-theprotocol-registry.md
- Homepage: https://github.com/https://api.theprotocol.cloud/mcp/sse
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server auth posture: open
- Server rate-limited: yes
- Parameters: 3 (1 required)
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `suite_id` | integer | yes | Eval suite id (e.g. forge-code-v1) |
| `agent_jwt` | string | no | Optional: agent JWT from getAgentToken. |
| `target_did` | string | no | Optional: evaluate this DID instead of yourself (needs forge.evolve_for_org) |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "theprotocol_runForgeEval",
    "arguments": {
      "suite_id": 0
    }
  }
}
```

## Why theprotocol_runForgeEval is rated High

theprotocol_runForgeEval triggers real processes with real consequences. An agent gone sideways doesn't fire it once. It starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.

## Use case

AI agents invoke theprotocol_runForgeEval to trigger actions in TheProtocol — Sovereign AI Agent Platform. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches TheProtocol — Sovereign AI Agent Platform:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "theprotocol_runForgeEval": {
      "limits": [
        {
          "counter": "theprotocol_runforgeeval_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on TheProtocol — Sovereign AI Agent Platform (412)

- `theprotocol_agentRevokeAttestation` — Destructive — https://policylayer.com/tools/cloud-theprotocol-registry/theprotocol-agentrevokeattestation.md
- `theprotocol_authForgotPassword` — Destructive — https://policylayer.com/tools/cloud-theprotocol-registry/theprotocol-authforgotpassword.md
- `theprotocol_authResetPassword` — Destructive — https://policylayer.com/tools/cloud-theprotocol-registry/theprotocol-authresetpassword.md
- `theprotocol_authSetNewPassword` — Destructive — https://policylayer.com/tools/cloud-theprotocol-registry/theprotocol-authsetnewpassword.md
- `theprotocol_cancelExchangeOrder` — Destructive — https://policylayer.com/tools/cloud-theprotocol-registry/theprotocol-cancelexchangeorder.md
- `theprotocol_changePassword` — Destructive — https://policylayer.com/tools/cloud-theprotocol-registry/theprotocol-changepassword.md
- `theprotocol_createTegPolicy` — Destructive — https://policylayer.com/tools/cloud-theprotocol-registry/theprotocol-createtegpolicy.md
- `theprotocol_crossRegistryContractProxy` — Destructive — https://policylayer.com/tools/cloud-theprotocol-registry/theprotocol-crossregistrycontractproxy.md
- `theprotocol_deleteBundle` — Destructive — https://policylayer.com/tools/cloud-theprotocol-registry/theprotocol-deletebundle.md
- `theprotocol_deleteFederationPeerSelf` — Destructive — https://policylayer.com/tools/cloud-theprotocol-registry/theprotocol-deletefederationpeerself.md
- `theprotocol_deleteMyAgent` — Destructive — https://policylayer.com/tools/cloud-theprotocol-registry/theprotocol-deletemyagent.md
- `theprotocol_deleteMyAgentByDev` — Destructive — https://policylayer.com/tools/cloud-theprotocol-registry/theprotocol-deletemyagentbydev.md
- `theprotocol_deleteMyApiKey` — Destructive — https://policylayer.com/tools/cloud-theprotocol-registry/theprotocol-deletemyapikey.md
- `theprotocol_deleteOrganization` — Destructive — https://policylayer.com/tools/cloud-theprotocol-registry/theprotocol-deleteorganization.md
- `theprotocol_deleteOrganizationTeam` — Destructive — https://policylayer.com/tools/cloud-theprotocol-registry/theprotocol-deleteorganizationteam.md
- `theprotocol_deletePipeline` — Destructive — https://policylayer.com/tools/cloud-theprotocol-registry/theprotocol-deletepipeline.md
- `theprotocol_deleteTegPolicy` — Destructive — https://policylayer.com/tools/cloud-theprotocol-registry/theprotocol-deletetegpolicy.md
- `theprotocol_deleteVersion` — Destructive — https://policylayer.com/tools/cloud-theprotocol-registry/theprotocol-deleteversion.md
- `theprotocol_deleteWebhook` — Destructive — https://policylayer.com/tools/cloud-theprotocol-registry/theprotocol-deletewebhook.md
- `theprotocol_disable2FASelf` — Destructive — https://policylayer.com/tools/cloud-theprotocol-registry/theprotocol-disable2faself.md
- `theprotocol_disableMyMtls` — Destructive — https://policylayer.com/tools/cloud-theprotocol-registry/theprotocol-disablemymtls.md
- `theprotocol_federationSlashRequest` — Destructive — https://policylayer.com/tools/cloud-theprotocol-registry/theprotocol-federationslashrequest.md
- `theprotocol_federationVetoProposal` — Destructive — https://policylayer.com/tools/cloud-theprotocol-registry/theprotocol-federationvetoproposal.md
- `theprotocol_finalizeFrameInvitation` — Destructive — https://policylayer.com/tools/cloud-theprotocol-registry/theprotocol-finalizeframeinvitation.md
- `theprotocol_guildCancelOrder` — Destructive — https://policylayer.com/tools/cloud-theprotocol-registry/theprotocol-guildcancelorder.md
- `theprotocol_logoutSession` — Destructive — https://policylayer.com/tools/cloud-theprotocol-registry/theprotocol-logoutsession.md
- `theprotocol_logTegDispute` — Destructive — https://policylayer.com/tools/cloud-theprotocol-registry/theprotocol-logtegdispute.md
- `theprotocol_operatorPortalSelfRestart` — Destructive — https://policylayer.com/tools/cloud-theprotocol-registry/theprotocol-operatorportalselfrestart.md
- `theprotocol_regenerateBackupCodes` — Destructive — https://policylayer.com/tools/cloud-theprotocol-registry/theprotocol-regeneratebackupcodes.md
- `theprotocol_removeOrganizationMember` — Destructive — https://policylayer.com/tools/cloud-theprotocol-registry/theprotocol-removeorganizationmember.md
- …and 382 more: https://policylayer.com/tools/cloud-theprotocol-registry.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=cloud-theprotocol-registry · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/cloud-theprotocol-registry