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.
This record as markdown: /tools/cloud-theprotocol-registry/theprotocol-runforgeeval.md
What theprotocol_runForgeEval does on TheProtocol — Sovereign AI Agent Platform
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.
| Parameter | Type | Required | Description |
|---|---|---|---|
suite_id | integer | Yes | Eval suite id (e.g. forge-code-v1) |
agent_jwt | string | — | Optional: agent JWT from getAgentToken. |
target_did | string | — | Optional: evaluate this DID instead of yourself (needs forge.evolve_for_org) |
Parameters from the server's own tool schema.
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.
Attacks that exploit this kind of access
The rule that runs theprotocol_runForgeEval safely
PolicyLayer is an MCP gateway: it sits between your AI agents and TheProtocol — Sovereign AI Agent Platform, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For theprotocol_runForgeEval, this is the rule to start with:
theprotocol_runForgeEval stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect TheProtocol — Sovereign AI Agent Platform, apply this rule, and every theprotocol_runForgeEval call is checked against it from then on.
Questions about 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. It is categorised as a Execute tool in the TheProtocol — Sovereign AI Agent Platform MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
theprotocol_runForgeEval accepts 3 parameters: suite_id, agent_jwt, target_did. Required: suite_id. The full parameter table on this page comes from the server's own tool schema.
Register the TheProtocol — Sovereign AI Agent Platform MCP server in PolicyLayer and add a rule for theprotocol_runForgeEval: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches TheProtocol — Sovereign AI Agent Platform. Nothing to install.
theprotocol_runForgeEval is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the theprotocol_runForgeEval rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for theprotocol_runForgeEval. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
theprotocol_runForgeEval is provided by the TheProtocol — Sovereign AI Agent Platform MCP server (https://api.theprotocol.cloud/mcp/sse). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on TheProtocol — Sovereign AI Agent Platform, and thousands of servers like it.
This server
Across the catalogue