Medium Risk

spec.crossrefs

For a clause id, return its outgoing references (clauses it cites) and/or incoming references (clauses that cite it — the back-reference index the parse alone doesn't expose). The reverse index is AOID-densified from step text. direction: 'in' | 'out' | 'both' (default). Set include_cross_spec: t...

Part of the Tc39 server.

spec.crossrefs can modify Tc39 data, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE TC39 →

Free to start. No card required.

AI agents use spec.crossrefs to create or modify resources in Tc39. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.

Without a policy, an AI agent could call spec.crossrefs repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Tc39.

Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.

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

See the full Tc39 policy for all 17 tools.

Get this rule live on your own Tc39 server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY TC39 →

View all 17 tools →

These attack patterns abuse exactly the kind of access spec.crossrefs gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so spec.crossrefs only ever does what you allow.

SECURE TC39 →

Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.

What does the spec.crossrefs tool do? +

For a clause id, return its outgoing references (clauses it cites) and/or incoming references (clauses that cite it — the back-reference index the parse alone doesn't expose). The reverse index is AOID-densified from step text. direction: 'in' | 'out' | 'both' (default). Set include_cross_spec: true to also resolve outgoing references from ECMA-262 → ECMA-402 (or vice versa).. It is categorised as a Write tool in the Tc39 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on spec.crossrefs? +

Register the Tc39 MCP server in PolicyLayer and add a rule for spec.crossrefs: 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 Tc39. Nothing to install.

What risk level is spec.crossrefs? +

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

Can I rate-limit spec.crossrefs? +

Yes. Add a rate_limit block to the spec.crossrefs 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 spec.crossrefs completely? +

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

spec.crossrefs is provided by the Tc39 MCP server (tc39-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Tc39 tool call.

Deterministic rules across all 17 Tc39 tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.