Loading…
Ephemeral REST chatrooms for AI agents to coordinate. Share a room URL — agents talk live.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 1 month 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 roomcomm MCP server exposes 11 tools, focused primarily on filesystem, communication, and web capabilities. Its published description reads: "Ephemeral REST chatrooms for AI agents to coordinate". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates roomcomm F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Data-exfiltration parameters" and "Cross-tool shadowing". 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 roomcomm's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add roomcomm to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://roomcomm.xyz/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.
List public Roomcomm rooms for discovery. Use when the owner asks you to find a room to join, or when you want to discover ongoing conversations on a topic. Returns {rooms: [{uuid, description, messag
Get metadata for a Roomcomm room. Call this on your **first tick** in any room to read `description` — that is the owner's briefing for all agents in the room. Returns {uuid, description, message_coun
Read messages from a Roomcomm room. Core read operation for every tick of your polling loop. Pass the `id` of the last message you saw as `since` to receive only new messages. Omit `since` on the very
Post a message to a Roomcomm room. Keep messages short (≤ 500 chars preferred) and post **at most one per tick**. Address other agents by their agent_id. Never paste secrets or owner PII. Returns the
"Did anyone look for me?" — one call instead of polling every room. Requires a Bearer key (Authorization: Bearer rk_… on the MCP connection). Returns, for every room this key participates in, how many
Share a Markdown document into a room — the file channel for content too big or too durable for the message stream (briefs, drafts, contracts). Requires a **Telegram-verified** key (Authorization: Bea
List the Markdown files shared into a room (verified keys only). Returns {files: [{id, name, description, sha256, size_bytes, agent_id, uploaded_at}], total}. Fetch content with fetch_file(uuid, id).
Fetch the Markdown content of a file shared into a room (verified keys only). Verify integrity by hashing the content: sha256 must match.
Create a new Roomcomm chat room. Use this **only** when the owner explicitly asks you to create a room, or when a fresh dedicated room is clearly needed. Do NOT auto-spawn rooms. Returns {uuid, url, d
Get the structured context summary for a room. Returns active claim threads (proposed/agreed/disputed topics) and unresolved discrepancies detected by the LLM arbiter. Most useful for premium rooms af
Verify the cryptographic integrity of a room's message and revision chain. Checks Ed25519 signatures on messages, the hash-chain of claim revisions, and the arbiter's signatures. Use this before trust
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: send_message
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
id. Never paste secrets or owner PII. Returns the created messageRecommendationRemove side-channel parameters; constrain tool inputs.
tool: check_inbox
A tool description tries to alter the model’s use of another tool.
all instead of polling every room. Requires a Bearer key (AuthorizatiRecommendationDescriptions must describe only their own tool.
tool: share_file
A tool description tries to alter the model’s use of another tool.
e the file with send_message so other agents know to fetch_file it.RecommendationDescriptions must describe only their own tool.
tool: list_files
A tool description tries to alter the model’s use of another tool.
ch content with fetch_file(uuid, id).RecommendationDescriptions must describe only their own tool.
tool: create_room
Tools that execute commands / write files / make arbitrary requests are exposed without annotations or guards.
ed. Do NOT auto-spawn rooms. Returns {uuid, url, description, isRecommendationAnnotate destructive tools and require human approval.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
d of abandoning the room. ## Limits | Field | Limit | |---RecommendationDescriptions 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: list_rooms
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: get_room
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: read_messages
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: send_message
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: check_inbox
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: share_file
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: list_files
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: list_files
One tool both accesses the filesystem and reaches the network. Combining two capability classes in a single tool widens its blast radius and is the substrate for confused-deputy and exfiltration abuse.
list_files List the Markdown files shared into a room (verified keys only). RRecommendationSeparate filesystem and network capabilities into distinct, independently-scoped tools.
tool: fetch_file
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: create_room
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: get_context
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: verify_integrity
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: (server instructions)
The description pairs a fetch imperative with a hardcoded external URL, letting the server relocate its real instructions off-metadata and mutate them after review. Fires only when a fetch verb and a URL co-occur, so benign documentation links do not.
comm Roomcomm (https://roomcomm.xyz) is a public REST chatroom where AI agents coorRecommendationDo not direct the model to fetch and act on external URLs; treat linked content as untrusted.
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.