Medium Risk

build_corpus

Pack a slice of project context into a persistent corpus on disk so future query_corpus calls can prime an LLM with the same snapshot without re-running the pack pipeline. Mutates the corpora store; returns JSON with the saved manifest. Pair with query_corpus for

How to control build_corpus ↓

AI agents use build_corpus to create or update resources in Trace — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Trace environment.

Medium Risk

The tool writes a new persistent corpus file to disk and mutates the corpora store. This is a reversible write operation (the corpus can be deleted), not destructive. The blast radius is medium since it writes persistent data to disk that affects future LLM queries, but does not execute code or delete anything.

From the tool's definition Pack a slice of project context into a persistent corpus on disk... Mutates the corpora store; returns JSON with the saved manifest.

Documented attack patterns abuse exactly the kind of access build_corpus gives an agent:

PolicyLayer is an MCP gateway — it sits between your AI agents and Trace, and nothing reaches the server without passing your rules. This is the rule we recommend for build_corpus:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "build_corpus": {
      "limits": [
        {
          "counter": "build_corpus_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

build_corpus stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Trace — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Go deeper

What does the build_corpus tool do? +

Pack a slice of project context into a persistent corpus on disk so future query_corpus calls can prime an LLM with the same snapshot without re-running the pack pipeline. Mutates the corpora store; returns JSON with the saved manifest. Pair with query_corpus for. It is categorised as a Write tool in the Trace MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on build_corpus? +

Register the Trace MCP server in PolicyLayer and add a rule for build_corpus: 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 Trace. Nothing to install.

What risk level is build_corpus? +

build_corpus is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit build_corpus? +

Yes. Add a rate_limit block to the build_corpus 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.

How do I block build_corpus completely? +

Set action: deny in the PolicyLayer policy for build_corpus. 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.

What MCP server provides build_corpus? +

build_corpus is provided by the Trace MCP server (nikolai-vysotskyi/trace-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Trace tool call.

Deterministic rules across all 178 Trace tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

178 Trace tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.