Low Risk

search_enriched

Full AI-powered government procurement search with Claude Sonnet intelligence. Returns a compact ranked summary of 10 matches showing title, match score, region, type, value, and deadline. Costs 1 credit. Always searches globally across all sources to find the best matches. After reviewing the su...

Part of the GovRider server.

search_enriched is read-only, but an agent in a loop can still rack up calls and cost. PolicyLayer caps every call before it runs. Live in minutes.

SECURE GOVRIDER →

Free to start. No card required.

AI agents call search_enriched to retrieve information from GovRider without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

Even though search_enriched only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "search_enriched": {}
  }
}

See the full GovRider policy for all 4 tools.

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

ENFORCE ON MY GOVRIDER →

These attack patterns abuse exactly the kind of access search_enriched 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 search_enriched only ever does what you allow.

SECURE GOVRIDER →

Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.

What does the search_enriched tool do? +

Full AI-powered government procurement search with Claude Sonnet intelligence. Returns a compact ranked summary of 10 matches showing title, match score, region, type, value, and deadline. Costs 1 credit. Always searches globally across all sources to find the best matches. After reviewing the summary, use get_opportunity with a result number (1-10) to see the full strategic fit memo, political context memo, description, and application URL for any match - at no extra cost.. It is categorised as a Read tool in the GovRider MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on search_enriched? +

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

What risk level is search_enriched? +

search_enriched is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit search_enriched? +

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

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

search_enriched is provided by the GovRider MCP server (@govrider/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every GovRider tool call.

Deterministic rules across all 4 GovRider 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.