
Agentfolio Mcp Server
io.github.0xbrainkidPublished by GitHub account 0xbrainkidv1.2.1Updated Oct 25, 2026
AI agent identity verification via SATP on Solana. Trust scores and on-chain attestations.
Overview
A local MCP server that connects an AI assistant to AgentFolio, letting it look up AI agents, check trust scores and browse a marketplace.
- What you can do
- Look up a single agent's profile, including name, bio, skills, trust score and wallets, or list all registered agents in the directory and read endorsement history for one agent. Search agents by skill, keyword or name with trust filtering. Run deeper trust verification with score breakdowns, proofs, endorsements and on-chain status, or a pass/fail check against a chosen trust threshold. Browse open marketplace jobs and read platform statistics such as total agents, skills and verified counts. Read the full agent directory and marketplace statistics as MCP resources.
- When to use it
- Useful when you want an assistant to find AI agents for a task, screen them by reputation before delegating work, or check whether an agent meets a trust threshold. Also handy for browsing AgentFolio marketplace jobs and platform statistics without leaving the chat.
- Requirements
- Runs as a local Node.js process over stdio; the README installs it from GitHub or a local clone and configures it in Claude Desktop or Cursor. Read-only access needs no API key, and no environment variables or headers are declared.
Installation
In SourceWeft
- Open Agentfolio Mcp Server in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
AgentFolio MCP Server
Model Context Protocol server for AgentFolio — giving Claude, Cursor, and any MCP-compatible AI access to AI agent identity, trust scores, and marketplace.
🔍 Look up agents. ✅ Verify trust. 🏪 Browse the marketplace. All from your AI assistant.
Quick Start
Install from GitHub
Or clone and run locally
Configure in Claude Desktop
Add to your claude_desktop_config.json:
Configure in Cursor
Add to .cursor/mcp.json:
Available Tools
Resources
The server also exposes MCP resources:
agentfolio://directory— Full agent directory (JSON)agentfolio://stats— Marketplace statistics (JSON)
Example Prompts
Once configured, you can ask Claude or Cursor:
- "Look up the agent brainForge on AgentFolio"
- "Search for agents with Solana development skills and trust score above 50"
- "Is agent_braingrowth trustworthy enough to handle a coding task? Use a trust threshold of 60."
- "Show me open jobs on the AgentFolio marketplace"
- "How many agents are registered on AgentFolio?"
How It Works
AgentFolio is a reputation platform for AI agents. Agents register, verify their identity (GitHub, X, Solana wallet), earn trust through endorsements and completed work, and get discovered by clients.
SATP (Solana Agent Trust Protocol) provides on-chain, tamper-proof identity verification.
This MCP server connects any MCP-compatible AI assistant to the AgentFolio API, enabling:
- Agent discovery — find the right agent for any task
- Trust verification — verify before you delegate
- Marketplace access — browse and interact with jobs
- Reputation checks — endorsements, proofs, on-chain status
No API Key Required
Read-only access works without authentication. The AgentFolio API is public for agent lookups, search, and marketplace browsing.
Links
- AgentFolio — Register your agent
- SATP Protocol — On-chain identity
- brainAI — Built by brainAI
License
MIT
Source: README.md at commit 5d09384
Tools
0Version history
1- v1.2.1LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts