search_bills

Full-text search US state (and federal) legislation to find out what bills are about a given topic. Searches one state or nationwide (ALL) and returns matching bills with number, title, state, last action, and a LegiScan bill_id you can pass to get_bill. Example: search_bills({ query: "data priva...

Server Legiscan pipeworx-io/mcp-legiscan
Category Read
Risk class Low
Parameters 41 required

What search_bills does on Legiscan

AI agents call search_bills to retrieve information from Legiscan without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

ParameterTypeRequiredDescription
year number LegiScan year code: 1 = all years, 2 = current + prior session (default), or a specific year like 2024.
query string Yes Search terms, e.g. "data privacy", "minimum wage", "abortion"
state string 2-letter state abbreviation (e.g. "CA", "TX") or "ALL" to search every state. Default "ALL".
_apiKey string Optional — your own LegiScan API key for higher limits; omit to use the shared Pipeworx key.

Parameters from the server's own tool schema.

Why search_bills needs a policy

This tool queries legislative data and retrieves results without side effects. It is a read-only search operation that returns bill information. No data is created, modified, deleted, or executed. The blast radius of misuse is minimal—an AI agent could only retrieve information already publicly available through the LegiScan API.

From the tool's definition Tool performs 'Full-text search' and 'returns matching bills' with metadata. No modification, deletion, or execution of code/commands occurs. The description uses search/query/return verbs typical of retrieval operations.

Risk signalsAccepts freeform code/query input (query)

Questions about search_bills

What does the search_bills tool do? +

Full-text search US state (and federal) legislation to find out what bills are about a given topic. Searches one state or nationwide (ALL) and returns matching bills with number, title, state, last action, and a LegiScan bill_id you can pass to get_bill. Example: search_bills({ query: "data privacy", state: "CA" }). It is categorised as a Read tool in the Legiscan MCP Server, which means it retrieves data without modifying state.

What parameters does search_bills accept? +

search_bills accepts 4 parameters: year, query, state, _apiKey. Required: query. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on search_bills? +

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

What risk level is search_bills? +

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

Can I rate-limit search_bills? +

Yes. Add a rate_limit block to the search_bills 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_bills completely? +

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

search_bills is provided by the Legiscan MCP server (pipeworx-io/mcp-legiscan). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER SERVER

Every MCP server has a record like this.

Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.