Navigate the U.S. Capitol complex — decode room codes, route between buildings, and check access and amenities.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 8 days ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The capitolguide MCP server exposes 9 tools, focused primarily on general-purpose capabilities. Its published description reads: "Navigate the U.S". It communicates over Streamable HTTP using the 2026-07-28 protocol revision, and does not require authorization to connect. MCPGrade currently rates capitolguide F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Data-exfiltration parameters" and "Metadata dictates tool-call ordering". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check capitolguide's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add capitolguide to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://capitol.guide/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
Pre-flight readiness check. Run before any other tool. Verifies secrets, KV, DB connectivity, and KB version + freshness. Returns a structured readiness report.
Operational snapshot for the caller's tenant: KB version + freshness, queue depths (itineraries / draft meetings / active nudges), and the recent tool-invocation tail. Read-only.
Find a Capitol office by ROOM CODE (e.g. 'SH-217', '2310 Rayburn', '167 Russell', 'H-232'), by MEMBER NAME (e.g. 'Cornyn', 'Ted Cruz', 'Womack'), or by COMMITTEE ('Senate Judiciary', 'Ways and Means',
Turn-by-turn directions between two points in the Capitol complex. Each point can be a room code, a building name, OR a Metro station / landmark (e.g. 'Capitol South Metro' → '2412 Rayburn', 'Union St
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: capitolguide_prep
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
tool. Verifies secrets, KV, DB connectivity, and KB version + freshnesRecommendationRemove side-channel parameters; constrain tool inputs.
tool: capitolguide_prep
The text tells the model WHEN to call this tool relative to others ("always call first", "before any other tool", "chain to X tool") — a toxic-flow injection that hijacks the agent’s orchestration rather than describing the tool.
ness check. Run before any other tool. Verifies secrets, KV, DB connectivity, and KBRecommendationTool metadata must describe only the tool, never sequence the agent’s calls.
tool: route_between
A tool description tries to alter the model’s use of another tool.
e route (or use accessible_route).RecommendationDescriptions must describe only their own tool.
tool: accessible_route
A tool description tries to alter the model’s use of another tool.
nstead of route_between when step-free matters.RecommendationDescriptions must describe only their own tool.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
h no auth. Only capitolguide_prep and overview need a capability token (AuthorizaRecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: find_room
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: route_between
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: accessible_route
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: check_access
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: nearby
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: prohibited_items
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: plan_day
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Step-free / accessible directions between two points in the Capitol complex by mobility profile (wheelchair, limited_mobility, stroller, low_vision). Routes over elevators/ramps only, avoids stairs, a
What access a visitor needs for a zone of the Capitol complex: (visitor_type × zone) → allowed?, credential, escort, lead time, required docs, security entrance, and the granting authority. INFORMS, n
Nearest restroom, exit, and food for a specific point — a room code (floor-specific, e.g. the exact nearest bathroom to SH-217), a building name, or GPS coordinates {lat, lon}. Returns specific named
What you cannot bring into an area of the Capitol complex (security screening). zone: 'capitol_cvc' (the Capitol + Visitor Center — strictest, no food/water), 'gallery' (House/Senate galleries — no ph
Optimize a multi-meeting Hill day. Give a list of meetings (each a member name or room code, with an optional time like '10:30a'). Returns a sequenced itinerary: batched by chamber side to minimize cr