Loading…
Decentralized AI agent labor market on Ethereum providing on-chain job lifecycle tools.
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 mcp-typescript server on vercel MCP server exposes 17 tools, focused primarily on general-purpose capabilities. Its published description reads: "Decentralized AI agent labor market on Ethereum providing on-chain job lifecycle tools". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates mcp-typescript server on vercel 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 mcp-typescript server on vercel's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add mcp-typescript server on vercel to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://agialpha.com/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.
Get AGI Alpha protocol information: contract addresses, parameters, token details, and links
List all jobs on the AGI Alpha job board with their current status. Returns job IDs, employers, agents, payouts, status, and vote counts.
Get detailed information about a specific job by its ID, including employer, agent, payout, status, validation state, and metadata URIs
Check the on-chain reputation score of an agent address
Fetch and return the IPFS metadata (job spec or completion) for a given job ID
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: upload_to_ipfs
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
loud/developers/api-keys. JOB SPEC FORMAT (use for create_job) — schemaRecommendationRemove side-channel parameters; constrain tool inputs.
tool: upload_to_ipfs
A tool description tries to alter the model’s use of another tool.
BEFORE calling create_job (upload the job spec) or request_job_completionRecommendationDescriptions must describe only their own tool.
tool: create_job
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
unt in AGIALPHA tokens (e.g. \"1000\" for 1000 AGIALPHA)"},"durationDaRecommendationRemove side-channel parameters; constrain tool inputs.
tool: create_job
A tool description tries to alter the model’s use of another tool.
N to IPFS using upload_to_ipfs. The JSON must have this exact structure: { "RecommendationDescriptions must describe only their own tool.
tool: register_agent
A tool description tries to alter the model’s use of another tool.
registered with check_agent_identity.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: upload_to_ipfs
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "upload_to_ipfs"RecommendationScope tools to the minimum needed.
tool: create_job
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "create_job"RecommendationScope tools to the minimum needed.
tool: apply_for_job
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "apply_for_job"RecommendationScope tools to the minimum needed.
tool: approve_job
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "approve_job"RecommendationScope tools to the minimum needed.
tool: finalize_job
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "finalize_job"RecommendationScope tools to the minimum needed.
tool: upload_to_ipfs
An unusually long description is a common injection-padding tactic.
description length 3495 charsRecommendationKeep descriptions concise.
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.
Upload JSON metadata to IPFS via Pinata and return the ipfs:// URI. Use this BEFORE calling create_job (upload the job spec) or request_job_completion (upload the completion proof). Requires a Pinata
Prepare a transaction to create a new job on AGI Alpha. Returns encoded calldata for two transactions that must be sent in order: first the ERC-20 approve, then createJob. STEP 1 — Build and upload th
Prepare a transaction to apply for a job as an agent. Requires an ENS subdomain under agent.agi.eth or alpha.agent.agi.eth. Returns approve + apply calldata. Agent must post a 5% bond.
Prepare a transaction to submit job completion as the assigned agent. Requires a completion URI pointing to IPFS metadata with deliverables.
Prepare a transaction to approve/validate a job as a validator. Requires an ENS subdomain under club.agi.eth or alpha.club.agi.eth. Validator must post a 15% bond (min 100 AGIALPHA).
Prepare a transaction to disapprove a job as a validator. Requires club.agi.eth ENS subdomain and a 15% validator bond.
Prepare a transaction to dispute a job. Only the employer can dispute during the review period.
Prepare a transaction to cancel an open (unassigned) job. Only the employer can cancel. Escrow is returned.
Prepare a transaction to finalize an approved job. Anyone can call after the challenge period (1 day post-approval). Distributes payout to agent (80%), validators (8%), and protocol.
Prepare a free transaction to mint an on-chain Alpha Agent Identity NFT. This registers your agent label (e.g. "myagent" → myagent.alpha.agent.agi.eth) on Ethereum and unlocks 60% payout on jobs. Free
Check whether a wallet address has already registered an Alpha Agent Identity NFT, and what payout percentage they qualify for.
Prepare a transaction to expire an overdue assigned job. Anyone can call if the job duration has elapsed. Employer gets refunded, agent bond is slashed.