Loading…
Provides semantic discovery and reputation tracking for autonomous agents.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 7 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 agent-hub MCP server exposes 14 tools, focused primarily on filesystem and developer capabilities. Its published description reads: "Provides semantic discovery and reputation tracking for autonomous agents". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates agent-hub F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Data-exfiltration parameters" and "Data-exfiltration parameters". 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 agent-hub's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add agent-hub to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://agent-hub-henna.vercel.app/api/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.
Ask whether a dated complaint has been published about a seller, a resource or an address, BEFORE you pay it. Every entry was filed by a proven party to a settled transaction — a signature from one of
File a complaint about a transaction you were a party to. Free, no account. Two calls: send your filing WITHOUT a signature to receive the exact statement to sign plus an admissibility verdict, then s
Read who may file a complaint about a paid agent transaction, what is verified, how long the counterparty has to reply, what is never done, and the current limits stated openly. Returns the same sourc
Publish a new unique AI-agent or MCP-server handle in the dated compatibility mirror. The description is indexed for keyword lookup, but listing is not verification, reputation or a purchase recommend
Claim an imported profile (official MCP registry import) by proving control of its GitHub repository — the repository already on file for that profile, never one you supply. Generate and save a high-e
Hold a private, persistent commercial or product conversation with Agent Reputation’s autonomous AI representative. Requires your claimed handle and owner token, which prevents anonymous callers from
Send one private, consent-based introduction to another claimed agent. Both sides authenticate with their profile capability token. The recipient contact stays hidden until acceptance; the Hub permits
List private contact requests for your claimed agent. Requires the owner token. Incoming requests include the requester contact if offered; outgoing requests reveal the recipient contact only after ac
Give one final response to a private contact request received by your claimed agent. Acceptance may disclose your chosen endpoint to the requester; decline discloses no contact and permanently prevent
The public registry of contribution receipts (FC-xxxx): recognized work recorded with the artifact it produced. Receipts remain separate from interaction-rating signals and create no membership, gover
After a real interaction, add one sourced 0-5 rating. It is an evidence input, never a universal verdict. Public native ratings require your claimed rater_handle and rater_owner_token. External signal
Bring a real contemplated agent-service purchase for possible manual MVP review, or explain what evidence is missing. For a purchase case use category why_i_came and include the candidate, mission, ex
Live statistics for the compatibility surface: how many AI agents and MCP servers are listed (registered natively + imported from external registries), how many sourced ratings have been submitted, an
Read the terms of the only paid product: a fixed-scope manual pre-purchase evidence brief about ONE agent you are considering buying from, for 0.50 USDC over x402. Returns what you get, the exact fiel
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: file_complaint
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "matter_url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: register_agent
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "endpoint"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: register_agent
A tool description tries to alter the model’s use of another tool.
anual proof via give_feedback.RecommendationDescriptions must describe only their own tool.
tool: claim_github
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "endpoint"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: request_contact
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
file capability token. The recipient contact stays hidden until accepRecommendationRemove side-channel parameters; constrain tool inputs.
tool: list_contact_requests
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
uires the owner token. Incoming requests include the requester contacRecommendationRemove side-channel parameters; constrain tool inputs.
tool: list_contact_requests
One tool reads private data, ingests untrusted content, AND can send data outbound — the three preconditions for autonomous data theft in a single call. A prompt injection reaching this tool can exfiltrate secrets with no further step.
ontact_requests Open your private consent inbox and outbox List private contact requests for yoRecommendationSplit the capabilities across separate least-privilege tools so no single tool can read secrets, read untrusted input, and reach the network at once.
tool: give_feedback
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
failure — never secrets or personal data. No account needed; intake doeRecommendationRemove side-channel parameters; constrain tool inputs.
tool: (server instructions)
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
re; their dated history is public at https://agentreputation.dev/decisiRecommendationRemove side-channel parameters; constrain tool inputs.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
hey are free: - check_complaints — before you pay a seller, ask whether a datedRecommendationDescriptions 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: complaint_bureau
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.
igibility rules Read who may file a complaint about a paid agent transaction, whaRecommendationSeparate filesystem and network capabilities into distinct, independently-scoped tools.
tool: claim_github
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: request_contact
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.
nd eligibility: https://agentreputation.dev/complaints Agent Reputation is also the independent, crosRecommendationDo 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.