reindex_project · Semantic Context MCP: Risk & Policy

WHAT IT DOES

What reindex_project does on Semantic Context MCP

AI agents invoke reindex_project to trigger actions in Semantic Context MCP. 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.

WHY IT NEEDS A POLICY

Why reindex_project needs a policy

This tool executes a batch reindexing process that modifies system state (rebuilding indices, computing embeddings for all contexts). While it doesn't delete data (not Destructive) or move money (not Financial), it runs a significant backend operation whose effects depend on project scope and context volume.

From the tool's definition Tool description states it will "backfill semantic embeddings for all existing contexts" — an operation that processes and transforms data across a project's historical records.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

reindex_project Rate-limited

reindex_project 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "reindex_project": {
      "limits": [
        {
          "counter": "reindex_project_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Semantic Context MCP, so you can run agents against it safely.

FAQ

Questions about reindex_project

What does the reindex_project tool do? +

Backfill semantic embeddings for all existing contexts in a project — run once to enable semantic search on historical snapshots. It is categorised as a Execute tool in the Semantic Context MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on reindex_project? +

Register the Semantic Context MCP server in PolicyLayer and add a rule for reindex_project: 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 Semantic Context MCP. Nothing to install.

What risk level is reindex_project? +

reindex_project is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit reindex_project? +

Yes. Add a rate_limit block to the reindex_project 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 reindex_project completely? +

Set action: deny in the PolicyLayer policy for reindex_project. 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 reindex_project? +

reindex_project is provided by the Semantic Context MCP server (semanticintent/semantic-wake-intelligence-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.