agentstamp MCP Server
Identity certificates, public registry, and wishing well for AI agents — x402 micropayments on Base
What is the agentstamp MCP Server?
The agentstamp MCP server gives AI agents structured, permission-aware access to agentstamp through the Model Context Protocol. With 19 pre-built actions, agents can read, create, and update agentstamp data on behalf of authorized users.
Willow ships the agentstamp MCP server as part of an enterprise control plane. Every call runs behind SSO (Okta, Azure AD), enforces RBAC and least-privilege at runtime, writes to a full audit trail, and integrates with Splunk and Loki for SIEM visibility. Connect from Claude Desktop, Claude Code, Cursor, ChatGPT, VS Code, n8n, or any custom agent. Install once, distribute org-wide, and see exactly how agentstamp is being used by every AI agent in your stack.
Tools
search_agents
Search the AgentStamp agent directory by query and/or category. Returns agents with reputation scores.
get_agent
Get full agent profile by ID, including endorsements and reputation score.
verify_stamp
Verify an AgentStamp identity certificate by its stamp ID.
browse_agents
Browse registered agents with optional category filter and sorting.
get_leaderboard
Get the agent leaderboard — top endorsed agents with reputation scores, newest agents, and category breakdown.
browse_wishes
Browse wishes from the Wishing Well. Discover what capabilities AI agents want.
get_trending
Get trending wish categories and velocity from the Wishing Well.
get_agent_reputation
Get an agent's reputation score (0-100) with full breakdown by tier, endorsements, uptime, age, and wishes granted.
get_passport
Get a signed cross-protocol agent passport. Contains identity, stamp, reputation, A2A card, and MCP metadata — all Ed25519-signed.
trust_check
Single-call trust verdict for any wallet address. Returns whether the agent is trusted, their score, tier, and profile info. Unregistered agents get trusted: false with a registration CTA.
trust_compare
Compare trust scores of up to 5 wallets side-by-side. See who leads, the score gap, and which agents are unregistered.
trust_network
Network-wide trust statistics: total agents, stamps, endorsements, wishes, average reputation, top categories. Social proof for the AgentStamp network.
bridge_erc8004_lookup
Look up an ERC-8004 on-chain agent and get their AgentStamp trust score. Free. Returns on-chain identity + trust verdict.
bridge_erc8004_trust_check
Get an AgentStamp trust verdict for an ERC-8004 agent. Free. Returns trusted/untrusted with score.
compliance_report
Get EU AI Act compliance report for an agent. Returns risk level, transparency declaration, audit summary, and trust status. Free.
get_verifiable_credential
Get a W3C Verifiable Credential for an agent. Returns the agent passport in W3C VC Data Model 2.0 format, interoperable with any VC verifier. Free.
dns_discovery
Check if a domain has an AgentStamp DNS TXT record for agent discovery. Verifies _agentstamp.domain.com TXT record and cross-checks with the registry. Free.
team_trust_check
Trust verdict for a multi-agent team. Returns aggregate trust score (0-100), weakest-link analysis, and per-member breakdown. Teams with score >= 10 and 2+ members are considered trusted.
create_team
Create a new agent team for multi-agent trust scoring. Owner is auto-added as first member. Note: for production use, prefer the REST API (POST /api/v1/teams) which requires wallet signature verification.
Customize Tools
Edit descriptions, modify arguments, select tools, or add new ones
Edit descriptions
Change arguments
Select tools
Set Up Your agentstamp MCP Server in Minutes
Add the following configuration to your MCP client. Authentication is handled via OAuth. Compatible with Claude Desktop, Claude Code, Cursor, ChatGPT, VS Code, n8n, and any MCP-compatible agent.
Claude Desktop
{
"mcpServers": {
"willow-agentstamp": {
"type": "http",
"url": "https://<org>.mcp-s.com/mcp/mcp/agentstamp"
}
}
}Cursor
{
"mcpServers": {
"willow-agentstamp": {
"type": "http",
"url": "https://<org>.mcp-s.com/mcp/mcp/agentstamp"
}
}
}Claude Code
claude mcp add willow-agentstamp --transport http https://<org>.mcp-s.com/mcp/mcp/agentstampn8n
{
"url": "https://<org>.mcp-s.com/mcp/mcp/agentstamp",
"method": "POST"
}Or click "Install with Willow" above to set up automatically with SSO and RBAC preconfigured.
Enterprise Governance for agentstamp
Willow adds the layer agentstamp and every other SaaS doesn't ship out of the box: every call runs behind SSO (Okta, Azure AD), enforces RBAC and least-privilege at runtime, writes to full audit logs, and detects shadow AI usage across your stack. One MCP gateway. Any agent. Every tool.
agentstamp MCP Server FAQ
What is the agentstamp MCP server?
The agentstamp MCP server is a Model Context Protocol implementation that lets AI agents like Claude, Cursor, and ChatGPT read and write agentstamp data through a standardized interface. Willow hosts and governs this server so enterprises can roll it out without a security review backlog.
How is Willow's agentstamp MCP server different from the official one?
The official agentstamp MCP server is scoped to a single user's account and does not include enterprise governance. Willow's version adds SSO, RBAC, audit logging, shadow AI detection, and centralized control over which actions agents can take across the entire org.
Which AI clients work with the agentstamp MCP server?
Claude Desktop, Claude Code, Cursor, ChatGPT, VS Code with MCP support, n8n, and any custom agent built with OpenAI Agents SDK, LangChain, Vercel AI SDK, or Anthropic SDK.
Is the agentstamp MCP server secure? How does Willow handle authentication?
Every call runs behind your existing SSO (Okta, Azure AD). Per-user OAuth scopes the agent to exactly what that user can do in agentstamp, nothing more. No credentials reach the LLM. Every action writes to an audit trail.
Can I limit which agentstamp actions agents can take?
Yes. Willow lets you scope agents to specific actions, specific projects, or specific environments. Toggle actions on or off in the dashboard, or enforce policy via infrastructure-as-code through GitHub.
How do I detect shadow agentstamp MCP servers in my org?
Willow's browser extension and discovery service surface unmanaged MCP servers, skills, and AI agents across the org. If a developer installed an unapproved agentstamp MCP locally, you'll see it.
What does the agentstamp MCP server cost?
Pricing depends on org size and deployment model (SaaS, dedicated cloud, self-host). See withwillow.ai/pricing or contact sales for a quote.
How do I install the agentstamp MCP server with Willow?
Install via the Willow Connect Panel in one click, or paste the JSON snippet above into your Claude Desktop, Cursor, or Claude Code config. SSO and RBAC inherit from your existing Willow setup.
Compare Willow MCP Gateway
See how Willow stacks up against other MCP platforms on governance, security, and enterprise readiness.
Your agents are already in the wild.
Give them a Basecamp. Go from AI chaos to AI work, in minutes.