congressgov-mcp-server

Congress.gov CRS Reports

congressgov_crs_reports

Read-onlyIdempotent

Browse and retrieve CRS (Congressional Research Service) reports — nonpartisan policy analyses by subject-matter experts at the Library of Congress, covering policy areas, legislative proposals, and legal questions. Report IDs use letter-number codes (e.g., R40097, RL33612, IF12345). Use 'list' to browse available reports or 'get' for full detail (authors, topics, summary, download formats).

Input Schema

Name	Required	Description
`limit`	No	Results per page (1-250).
`offset`	No	Pagination offset.
`operation`	Yes	Which data to retrieve.
`reportNumber`	No	CRS report ID (e.g., 'R40097'). Required for 'get'.

Output Schema

Name	Required	Description
`data`	No	Result rows. Per-tool item shape is rendered in the markdown body.
`error`	No	Present when the call failed. Absent on success.
`notice`	No	Guidance when results are empty, a page is past the end, or a caveat applies.
`report`	No	Dynamic upstream JSON record.
`pagination`	No	Pagination metadata: total count and next offset.
`totalCount`	No	Total results across all pages.
`effectiveQuery`	No	The browse scope and applied filters.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 2, 2026

changedOutput schema / properties / error / properties / data / properties / reason / description

Previous value: -"Machine-readable failure mode. Declared by this tool: `not_found`: A requested bill, member, committee, report, vote, or nomination does not exist in Congress.gov. `rate_limited`: A process-local attempt budget or the shared upstream credential/IP quota was reached; upstream hourly limits vary and DEMO_KEY also has a daily quota. `invalid_request`: Congress.gov rejected the request as malformed — a bad date range or an identifier with an unexpected shape. `upstream_error`: Congress.gov returned an unexpected error (5xx or another non-2xx status). `upstream_timeout`: The Congress.gov request deadline expired or the upstream returned an HTTP timeout response. `incompatible_identity`: A list operation carries an entity identifier that only a detail operation uses. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `not_found`: A requested bill, member, committee, report, vote, or nomination does not exist in Congress.gov. `rate_limited`: A process-local attempt budget or the shared upstream credential/IP quota was reached; upstream hourly limits vary and DEMO_KEY also has a daily quota. `invalid_request`: Congress.gov rejected the request as malformed — a bad date range or an identifier with an unexpected shape. `api_key_rejected`: The api.data.gov gateway rejected the server's configured CONGRESS_API_KEY (missing, invalid, disabled, unauthorized, or unverified); the gateway code is in data.upstreamCode. No change to the call's arguments can fix it. `upstream_error`: Congress.gov returned an unexpected error (5xx or another non-2xx status) or could not be reached, or the Senate LIS feed failed (5xx, a timeout, or a senate.gov HTTP 403 refusal, which carries retryable: false). `upstream_timeout`: A Congress.gov request or a congress.gov document fetch timed out or returned an HTTP timeout response, or the call's upstream requests could not finish inside its 50-second budget. `incompatible_identity`: A list operation carries an entity identifier that only a detail operation uses. Other values are possible when a failure originates below the handler."

changedOutput schema / properties / error / properties / data / properties / reason / examples

Previous value: -[
-  "not_found",
-  "rate_limited",
-  "invalid_request",
-  "upstream_error",
-  "upstream_timeout",
-  "incompatible_identity"
-]New value: +[
+  "not_found",
+  "rate_limited",
+  "invalid_request",
+  "api_key_rejected",
+  "upstream_error",
+  "upstream_timeout",
+  "incompatible_identity"
+]

Changed2 schema fields changedOct 13, 2026

changedOutput schema / properties / error / properties / data / properties / reason / description

Previous value: -"Machine-readable failure mode. Declared by this tool: `not_found`: A requested bill, member, committee, report, vote, or nomination does not exist in Congress.gov. `rate_limited`: The Congress.gov API rate limit (5,000 requests/hour per key) was exceeded. `invalid_request`: Congress.gov rejected the request as malformed — a bad date range or an identifier with an unexpected shape. `upstream_error`: Congress.gov returned an unexpected error (5xx or another non-2xx status). Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `not_found`: A requested bill, member, committee, report, vote, or nomination does not exist in Congress.gov. `rate_limited`: A process-local attempt budget or the shared upstream credential/IP quota was reached; upstream hourly limits vary and DEMO_KEY also has a daily quota. `invalid_request`: Congress.gov rejected the request as malformed — a bad date range or an identifier with an unexpected shape. `upstream_error`: Congress.gov returned an unexpected error (5xx or another non-2xx status). `upstream_timeout`: The Congress.gov request deadline expired or the upstream returned an HTTP timeout response. `incompatible_identity`: A list operation carries an entity identifier that only a detail operation uses. Other values are possible when a failure originates below the handler."

changedOutput schema / properties / error / properties / data / properties / reason / examples

Previous value: -[
-  "not_found",
-  "rate_limited",
-  "invalid_request",
-  "upstream_error"
-]New value: +[
+  "not_found",
+  "rate_limited",
+  "invalid_request",
+  "upstream_error",
+  "upstream_timeout",
+  "incompatible_identity"
+]

Changed1 schema field changedAug 30, 2026

addedOutput schema / properties / report

Added value: +{
+  "additionalProperties": {},
+  "description": "Dynamic upstream JSON record.",
+  "properties": {},
+  "type": "object"
+}

Changed6 schema fields changedAug 25, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

addedInput schema / additionalProperties
```
Added value: +false
```

changedOutput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

addedOutput schema / anyOf

Added value: +[
+  {
+    "not": {
+      "required": [
+        "error"
+      ]
+    },
+    "required": [
+      "effectiveQuery",
+      "totalCount"
+    ]
+  },
+  {
+    "required": [
+      "error"
+    ]
+  }
+]

addedOutput schema / properties / error

Added value: +{
+  "additionalProperties": {},
+  "description": "Present when the call failed. Absent on success.",
+  "properties": {
+    "code": {
+      "description": "JSON-RPC error code for this failure.",
+      "maximum": 9007199254740991,
+      "minimum": -9007199254740991,
+      "type": "integer"
+    },
+    "data": {
+      "additionalProperties": {},
+      "properties": {
+        "reason": {
+          "description": "Machine-readable failure mode. Declared by this tool: `not_found`: A requested bill, member, committee, report, vote, or nomination does not exist in Congress.gov. `rate_limited`: The Congress.gov API rate limit (5,000 requests/hour per key) was exceeded. `invalid_request`: Congress.gov rejected the request as malformed — a bad date range or an identifier with an unexpected shape. `upstream_error`: Congress.gov returned an unexpected error (5xx or another non-2xx status). Other values are possible when a failure originates below the handler.",
+          "examples": [
+            "not_found",
+            "rate_limited",
+            "invalid_request",
+            "upstream_error"
+          ],
+          "type": "string"
+        },
+        "recovery": {
+          "additionalProperties": {},
+          "description": "Actionable next step for the caller.",
+          "properties": {
+            "hint": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "hint"
+          ],
+          "type": "object"
+        },
+        "retryable": {
+          "description": "Whether retrying may succeed.",
+          "type": "boolean"
+        }
+      },
+      "type": "object"
+    },
+    "message": {
+      "description": "Human-readable description of what went wrong.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "code",
+    "message"
+  ],
+  "type": "object"
+}

removedOutput schema / required

Removed value: -[
-  "effectiveQuery",
-  "totalCount"
-]

Changed6 schema fields changedMay 30, 2026

removedOutput schema / description

Removed value: -"Detail-mode key 'report' carries: CRS report record for `get` (authors, topics, summary, formats, related materials); absent for `list`."

addedOutput schema / properties / effectiveQuery

Added value: +{
+  "description": "The browse scope and applied filters.",
+  "type": "string"
+}

addedOutput schema / properties / notice

Added value: +{
+  "description": "Guidance when results are empty, a page is past the end, or a caveat applies.",
+  "type": "string"
+}

removedOutput schema / properties / query

Removed value: -{
-  "description": "Echo of the applied filters for list-mode queries. Rendered as the first line of the response.",
-  "type": "string"
-}

addedOutput schema / properties / totalCount

Added value: +{
+  "description": "Total results across all pages.",
+  "type": "number"
+}

addedOutput schema / required

Added value: +[
+  "effectiveQuery",
+  "totalCount"
+]

Changed4 schema fields changedMay 21, 2026

changedOutput schema / description

Previous value: -"CRS report data from Congress.gov API."New value: +"Detail-mode key 'report' carries: CRS report record for `get` (authors, topics, summary, formats, related materials); absent for `list`."

addedOutput schema / properties / data

Added value: +{
+  "description": "Result rows. Per-tool item shape is rendered in the markdown body.",
+  "items": {
+    "additionalProperties": {},
+    "description": "Upstream JSON record. Per-tool item shape is rendered in the markdown body.",
+    "properties": {},
+    "type": "object"
+  },
+  "type": "array"
+}

addedOutput schema / properties / pagination

Added value: +{
+  "additionalProperties": false,
+  "description": "Pagination metadata: total count and next offset.",
+  "properties": {
+    "count": {
+      "description": "Total result count across all pages.",
+      "maximum": 9007199254740991,
+      "minimum": 0,
+      "type": "integer"
+    },
+    "nextOffset": {
+      "anyOf": [
+        {
+          "maximum": 9007199254740991,
+          "minimum": 0,
+          "type": "integer"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "Offset to pass for the next page, or null when there are no more pages."
+    }
+  },
+  "required": [
+    "count"
+  ],
+  "type": "object"
+}

addedOutput schema / properties / query

Added value: +{
+  "description": "Echo of the applied filters for list-mode queries. Rendered as the first line of the response.",
+  "type": "string"
+}

Changed3 schema fields changedApr 21, 2026

removedOutput schema / properties / data

Removed value: -{
-  "description": "CRS report list results when operation=\"list\". Preserves upstream item shapes instead of narrowing them.",
-  "items": {},
-  "type": "array"
-}

removedOutput schema / properties / pagination

Removed value: -{
-  "additionalProperties": false,
-  "description": "Pagination metadata for list results.",
-  "properties": {
-    "count": {
-      "description": "Total number of matching CRS reports.",
-      "maximum": 9007199254740991,
-      "minimum": 0,
-      "type": "integer"
-    },
-    "nextOffset": {
-      "anyOf": [
-        {
-          "maximum": 9007199254740991,
-          "minimum": 0,
-          "type": "integer"
-        },
-        {
-          "type": "null"
-        }
-      ],
-      "description": "Offset to request the next page, or null when there is no next page."
-    }
-  },
-  "required": [
-    "count",
-    "nextOffset"
-  ],
-  "type": "object"
-}

removedOutput schema / properties / report

Removed value: -{
-  "additionalProperties": {},
-  "description": "CRS report detail when operation=\"get\".",
-  "properties": {
-    "reportNumber": {
-      "description": "CRS report identifier when provided by Congress.gov.",
-      "type": "string"
-    },
-    "summary": {
-      "description": "CRS report summary when provided by Congress.gov. Omitted when unknown.",
-      "type": "string"
-    },
-    "title": {
-      "description": "CRS report title when provided by Congress.gov. Omitted when unknown.",
-      "type": "string"
-    },
-    "updateDate": {
-      "description": "Last update timestamp when provided by Congress.gov.",
-      "type": "string"
-    }
-  },
-  "type": "object"
-}

Changed3 schema fields changedApr 19, 2026

addedOutput schema / properties / data

Added value: +{
+  "description": "CRS report list results when operation=\"list\". Preserves upstream item shapes instead of narrowing them.",
+  "items": {},
+  "type": "array"
+}

addedOutput schema / properties / pagination

Added value: +{
+  "additionalProperties": false,
+  "description": "Pagination metadata for list results.",
+  "properties": {
+    "count": {
+      "description": "Total number of matching CRS reports.",
+      "maximum": 9007199254740991,
+      "minimum": 0,
+      "type": "integer"
+    },
+    "nextOffset": {
+      "anyOf": [
+        {
+          "maximum": 9007199254740991,
+          "minimum": 0,
+          "type": "integer"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "Offset to request the next page, or null when there is no next page."
+    }
+  },
+  "required": [
+    "count",
+    "nextOffset"
+  ],
+  "type": "object"
+}

addedOutput schema / properties / report

Added value: +{
+  "additionalProperties": {},
+  "description": "CRS report detail when operation=\"get\".",
+  "properties": {
+    "reportNumber": {
+      "description": "CRS report identifier when provided by Congress.gov.",
+      "type": "string"
+    },
+    "summary": {
+      "description": "CRS report summary when provided by Congress.gov. Omitted when unknown.",
+      "type": "string"
+    },
+    "title": {
+      "description": "CRS report title when provided by Congress.gov. Omitted when unknown.",
+      "type": "string"
+    },
+    "updateDate": {
+      "description": "Last update timestamp when provided by Congress.gov.",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

First observedMar 28, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent and openWorld, so the safety profile is covered. The description adds real behavioral context beyond that: the report ID convention (letter-number prefixes such as R/RL/IF) and the fact that 'get' surfaces authors, topics, summary and download formats. It says nothing about pagination behavior or rate limits, but pagination is covered by the schema.

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, zero filler: the resource is defined first, then the operation choice. Even the acronym expansion earns its place because it tells an agent what the content actually is.

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?

With an output schema, full parameter descriptions and rich annotations, the description only needs to carry purpose, operation choice and identifier format — all present. The missing piece is routing against congressgov_committee_reports, a sibling whose name an agent could easily confuse with this one.

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 description coverage is 100%, so the baseline is 3. The description contributes only a mild extra — showing multiple report-number prefixes (R40097, RL33612, IF12345) versus the schema's single example — which helps an agent construct a valid reportNumber but does not add much beyond structured fields.

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

Purpose4/5

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

States a specific verb pair (browse/retrieve) and a precisely scoped resource, and even explains what a CRS report is (nonpartisan policy analyses from the Library of Congress), which disambiguates the acronym. It does not, however, explicitly contrast itself with the similarly-named sibling congressgov_committee_reports.

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?

'Use list to browse available reports or get for full detail' gives a clear decision rule for the operation enum and names what 'get' returns. It offers no guidance on when to reach for this tool versus congressgov_committee_reports or congressgov_bill_summaries, which is the main remaining gap.

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

All congressgov-mcp-server tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.