Same door for humans and AI. No gatekeeper.Register →
Explorer/MCP/ferm-ai/agentwork-mcp
✓ REGISTRY VERIFIEDREMOTE◉ LIVE SCAN

io.github.ferm-ai/agentwork-mcp

ferm-ai/agentwork-mcp

Official MCP server for Agentwork — delegate tasks to AI agents with human-in-the-loop

9 tools available
Flagged
Our scanner found something that deserves a closer look. Check the Security Signals section below before connecting.
Time indexed (5mo)
9toolsRemote/ HTTP5moindexed2signals
Checked Sep 16, 2026
Quality Score
31/95
Emerging
Risk Score
36/100
Elevated
How is this calculated?
Quality Breakdown
Tenure13.7/20
151 days indexed
Capability17.1/25
Tools: 5.1/13 (9 tools)
Description: 5/5
Endpoint: 7/7
Adoption0/25
Use count: 0/20 (0 uses)
Multi-registry: 0/5 (1 registry)
Reliability0/25
Currently live: 0/10
Uptime history: 0/15 No checks yet
Security scan: 0 pts in v1.0; ready to weight when coverage improves
Incomplete Data Cap (60)
Usage data is not available for this server. Quality is capped until adoption can be measured.
Risk
36Elevated
See Security Signals section for details.
The scanner shows
9 tools. Our scanner detected injection patterns and authentication gaps. Review the Security Signals section before connecting.
First indexed Apr 18, 2026
Security Signals2 rule groups · 6 findings
Sensitive parameter names detected (5)High
"api_key" parameter in agentwork_create_task
"api_key" parameter in agentwork_get_task_status
"api_key" parameter in agentwork_send_message
"api_key" parameter in agentwork_approve_spec
"api_key" parameter in agentwork_approve_solution
No authentication requiredHigh
Server responded without authentication
Server Profile
Tools catalogued
9
9 tools available. Full list below.
Hosting
Remote / HTTP
Runs on the internet. No access to your filesystem, SSH keys, or environment variables.
Registry presence
Verified
Listed on the Official MCP Registry under Linux Foundation governance.
Liveness
No liveness checks recorded yet.
Publisher Verification
✓ Listed on the Official MCP Registry under Linux Foundation governance.
Published version: 0.1.3
Connect to this server
STREAMABLE-HTTP
https://mcp.agentwork.so/
Tools (9)We asked this server directly for its tool list on Apr 19.
agentwork_register
Register a new Agentwork account and get an API key. Call this first if you don't have an API key yet. You need to provide an email address and your full name. Args: email: Your email address (so the Agentwork team can contact you). name: Your full name. organization_name: Organization name (optional, auto-generated if omitted). Returns: JSON with api_key, organization_id, and user_id.
agentwork_create_task
Create a new task on Agentwork. Args: title: Short title for the task (max ~70 chars). description: Detailed description of what you need done. api_key: Your Agentwork API key. Returns: JSON with task_id and initial status.
agentwork_get_task_status
Check the current status of a task. The response tells you what action is needed: - "processing": The agent is working. Poll again later. - "awaiting_reply": The agent asked a question. Use agentwork_send_message to reply. - "awaiting_spec_approval": A plan was proposed. Use agentwork_approve_spec to accept/reject. - "awaiting_solution_approval": A solution was proposed. Use agentwork_approve_solution to accept/reject. - "completed": The task is done. Use agentwork_get_task_result to fetch the output. Args: task_id: The task ID returned by agentwork_create_task. api_key: Your Agentwork API key. Returns: JSON with task_id, title, status, and optional question/spec/solution details.
agentwork_send_message
Reply to a question from the Agentwork agent. Use this when agentwork_get_task_status returns status "awaiting_reply". This covers clarifying questions, accuracy level selection, and general follow-ups. Args: task_id: The task ID. message: Your reply to the agent's question. api_key: Your Agentwork API key. Returns: JSON with success status.
agentwork_approve_spec
Approve or reject the proposed spec/plan. Use this when agentwork_get_task_status returns status "awaiting_spec_approval". Args: task_id: The task ID. approved: True to approve, False to reject. api_key: Your Agentwork API key. rejection_reason: If rejecting, explain what changes you want. Returns: JSON with success and new status.
agentwork_approve_solution
Approve or reject the proposed solution. Use this when agentwork_get_task_status returns status "awaiting_solution_approval". Args: task_id: The task ID. approved: True to approve, False to reject. api_key: Your Agentwork API key. rejection_reason: If rejecting, explain what needs to change. Returns: JSON with success and new status.
Show all 9 tools ↓
agentwork_get_task_result
Fetch the completed result of a task (text + file URLs). Use this when agentwork_get_task_status returns status "completed". Args: task_id: The task ID. api_key: Your Agentwork API key. Returns: JSON with result_text and a list of downloadable files.
agentwork_get_task_events
Get the activity log for a task — see what the agent is doing in real-time. Returns timestamped events like status updates ("Searching the web..."), questions asked, replies sent, and spec/solution proposals. Useful for monitoring progress while status is "processing". Args: task_id: The task ID. api_key: Your Agentwork API key. Returns: JSON with a list of events, each having timestamp, type, and content.
agentwork_cancel_task
Cancel a running task. Args: task_id: The task ID to cancel. api_key: Your Agentwork API key. Returns: JSON with success status.

Is this your server?

Create a free RNWY account to connect your on-chain identity to this server. MCP server claiming is coming; register now and you'll be first in line.

Create your account →
Similar servers
AI/MCP Enablement Agency
AI workflow/MCP implementation package planner.
Taproot: AT Protocol MCP
Read public AT Protocol profiles, records, threads, backlinks and lexicons. No API key required.
remote-mcp-server-authless
Deploy a remote MCP server on Cloudflare Workers without requiring authentication.
io.github.attestd-io/attestd-mcp
CVE and supply chain checks for MCP clients. Covers infrastructure, PyPI, and npm packages.
cafecito
Enables AI agents to coordinate on a shared repository using commutativity-proven parallel landing and regenerative merge, avoiding rebase conflicts through symbol-level leases.
Korean Law MCP Server
Enables searching and retrieving Korean statutes, precedents, and constitutional court decisions via MCP, using the National Law Information Center API.
Indexed from Official MCP Registry · Updates nightly