Govinfo

Search Packages

search_packages

Read-onlyIdempotent

Full-text + faceted search across GovInfo. Filter by one or more collection codes (BILLS, FR, CFR, USCODE, CHRG, CRPT, CREC, PLAW, USCOURTS...), date range, congress, and free-text query. Several codes search the union of those collections. Returns package IDs, titles, collection and issue dates.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	Alias for page_size, 1-100.
`query`	Yes	Free-text search
`date_to`	No	YYYY-MM-DD
`congress`	No	Congress number (e.g., 118) — for BILLS/CHRG/CRPT
`date_from`	No	YYYY-MM-DD
`page_size`	No	Results per page, 1-100 (default 25). `limit` works as an alias.
`collections`	No	Collection codes, comma- or space-separated (e.g. "CHRG" or "CHRG,CRPT"). Several codes return the union of those collections — "CHRG,CRPT" gives every package in either. Codes come from list_collections.
`offset_mark`	No	Pagination cursor from previous response

Output Schema

TableJSON Schema

Name	Required	Description
`total`	Yes	Total matching packages
`results`	Yes	Search result packages
`returned`	Yes	Number of results returned in this response
`next_offset_mark`	No	Pagination cursor for next results

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed4 schema fields changedAug 27, 2026

changedInput schema / examples

Previous value: -[
-  {
-    "query": "climate change"
-  },
-  {
-    "collections": "BILLS,FR",
-    "congress": 118,
-    "date_from": "2023-01-01",
-    "date_to": "2024-12-31",
-    "page_size": 50,
-    "query": "environmental protection"
-  }
-]New value: +[
+  {
+    "query": "climate change"
+  },
+  {
+    "collections": "CHRG,CRPT",
+    "limit": 5,
+    "query": "Cooper"
+  },
+  {
+    "collections": "BILLS,FR",
+    "congress": 118,
+    "date_from": "2023-01-01",
+    "date_to": "2024-12-31",
+    "page_size": 50,
+    "query": "environmental protection"
+  }
+]

changedInput schema / properties / collections / description

Previous value: -"Comma-separated collection codes (e.g., \"BILLS,FR\")"New value: +"Collection codes, comma- or space-separated (e.g. \"CHRG\" or \"CHRG,CRPT\"). Several codes return the union of those collections — \"CHRG,CRPT\" gives every package in either. Codes come from list_collections."

addedInput schema / properties / limit

Added value: +{
+  "description": "Alias for page_size, 1-100.",
+  "type": "number"
+}

changedInput schema / properties / page_size / description

Previous value: -"1-100 (default 25)"New value: +"Results per page, 1-100 (default 25). `limit` works as an alias."

Changed2 schema fields changedMay 24, 2026

addedInput schema / examples

Added value: +[
+  {
+    "query": "climate change"
+  },
+  {
+    "collections": "BILLS,FR",
+    "congress": 118,
+    "date_from": "2023-01-01",
+    "date_to": "2024-12-31",
+    "page_size": 50,
+    "query": "environmental protection"
+  }
+]

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "next_offset_mark": {
+      "description": "Pagination cursor for next results",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "results": {
+      "description": "Search result packages",
+      "items": {
+        "properties": {
+          "collection": {
+            "description": "Collection code",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "collection_name": {
+            "description": "Collection name",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "date_issued": {
+            "description": "Issue date (ISO format)",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "details_link": {
+            "description": "URL to detailed metadata",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "last_modified": {
+            "description": "Last modified date",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "package_id": {
+            "description": "GovInfo package ID",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "package_link": {
+            "description": "URL to package on GovInfo",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "title": {
+            "description": "Package title",
+            "type": [
+              "string",
+              "null"
+            ]
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "returned": {
+      "description": "Number of results returned in this response",
+      "type": "number"
+    },
+    "total": {
+      "description": "Total matching packages",
+      "type": "number"
+    }
+  },
+  "required": [
+    "total",
+    "returned",
+    "results"
+  ],
+  "type": "object"
+}

First observedMay 13, 2026

TDQS

A4.2/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark the tool as read-only, idempotent, and non-destructive, so the bar is lower. The description adds useful behavioral context by explaining that collection codes search the union of collections and by listing the fields returned, complementing the annotations without contradicting them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences carry the entire functional description: the operation, the filters, the union nuance, and the return values. There is no filler, and the core action is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the output schema is present and the annotations cover safety, the description is sufficiently complete for invoking the tool: query, filters, and result fields are all stated. It could marginally improve by noting pagination behavior, but that is already covered by the schema's page_size and offset_mark parameters.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the schema already describes each parameter in reasonable detail, including the union behavior for collections. The description adds high-level meaning such as 'date range' and 'congress' but does not substantially extend the schema's parameter-level explanations.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Full-text + faceted search across GovInfo', which names a specific verb, resource, and scope. It goes on to enumerate the filter dimensions (collection codes, date range, congress, free-text) and the return shape (package IDs, titles, collection and issue dates), making it clear how this differs from more targeted package tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly establishes the intended use: searching across GovInfo packages by facets like collection, date, and congress. It does not explicitly name alternative tools or exclusion conditions, but the context is strong enough that an agent can infer when to prefer this tool over package-listing or granule-level tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Govinfo tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.8/5.0

Disambiguation2/5

Many tools have heavily overlapping purposes: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, discover_tools, and suggest_questions all serve lookup/discovery in similar ways, and the five polymarket_* tools plus bet_research blur together. The six genuinely GovInfo-specific tools are distinct, but an agent would struggle to pick between the numerous meta and market tools, especially when the server is supposed to be about government information.

Naming Consistency3/5

Most tools follow a readable verb_noun pattern (list_collections, search_packages, get_granule, resolve_entity), but there are deviations: domain-prefixed nouns like polymarket_arbitrage, noun-ish names like pipeworx_trending, and verb phrases like ask_pipeworx_beta or generate_llms_txt. Overall it is mixed yet still navigable, not chaotic.

Tool Count2/5

36 tools is excessive for a server named Govinfo: only about six tools (list_collections, search_packages, get_package, list_granules, get_granule, search_within) actually serve that domain, while the remaining ~30 are Pipeworx meta-tools, prediction-market helpers, memory utilities, and AI-visibility checks. The count is bloated relative to the apparent scope and dilutes the server's identity.

Completeness3/5

The core GovInfo workflow is present — list collections, search packages, fetch package metadata, list and fetch granules, and semantically search within fetched text. However, there is no tool that directly downloads or returns the full text/PDF/XML content of a package or granule; agents only get links, so a full-document workflow requires an external fetch. The unrelated tools do not fill that gap and instead distract from the domain.

Search Packages

Input Schema

Output Schema

Schema Changelog

TDQS

Glama MCP Gateway

TDQS

Resources