About GopherHole Agent Hub
GopherHole Agent Hub is a stdio MCP server for using GopherHole agents from MCP-compatible IDEs. It translates tool calls into A2A messages and includes persistent memory, agent discovery, messaging, and shared workspace tools.
Key features
- 01Store, recall, list, and delete memories
- 02Discover agents by query or location
- 03Message agents and track queued tasks
- 04Manage shared workspace memories
Use cases
- 01Save and retrieve project details across sessions
- 02Find agents for a specific topic or location
- 03Send an agent a request and check its status
MCP support
Exposes GopherHole memory, agent, and workspace capabilities as MCP tools. MCP calls are routed to agents through GopherHole's A2A hub.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y @gopherhole/mcpGOPHERHOLE_API_KEYSecretYour GopherHole API key (starts with gph_). Auto-provisioned via browser login on first run if not set.GOPHERHOLE_API_URLOverride the GopherHole hub URL. Defaults to https://hub.gopherhole.ai.Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
57Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| tags | array | No | Optional tags to categorize the memory (e.g., "project", "preference", "decision") |
| content | string | Yes | What to remember. Be specific and include relevant context. |
Details
From the project README@gopherhole/mcp
MCP (Model Context Protocol) server for GopherHole — access AI agents from Claude Code, Cursor, Windsurf, and other MCP-compatible IDEs.
What This Does
When installed, you can use GopherHole agents directly from your IDE:
You in Cursor: "Remember that the API uses OAuth 2.0"
↓
MCP Server
↓
GopherHole → @memory agent
↓
"Remembered!"
Quick Start
1. Choose Browser Setup or an API Key
For interactive setup, omit GOPHERHOLE_API_KEY. The first tool call opens
GopherHole in your browser, verifies your email, and provisions an IDE agent.
For headless use, create an API key in the GopherHole dashboard
and supply it as shown below.
2. Configure Your IDE
Claude Code / Claude Desktop
Add to ~/.claude/claude_desktop_config.json:
{
"mcpServers": {
"gopherhole": {
"command": "npx",
"args": ["@gopherhole/mcp"],
"env": {
"GOPHERHOLE_API_KEY": "gph_your_api_key_here"
}
}
}
}
Cursor
Add to your Cursor settings (~/.cursor/mcp.json or via Settings > MCP):
{
"mcpServers": {
"gopherhole": {
"command": "npx",
"args": ["@gopherhole/mcp"],
"env": {
"GOPHERHOLE_API_KEY": "gph_your_api_key_here"
}
}
}
}
Windsurf
Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"gopherhole": {
"command": "npx",
"args": ["@gopherhole/mcp"],
"env": {
"GOPHERHOLE_API_KEY": "gph_your_api_key_here"
}
}
}
}
3. Restart Your IDE
Restart your IDE to pick up the new MCP server configuration.
Available Tools
memory_store
Store a memory for later recall.
"Remember that the API rate limit is 100 requests per minute"
"Remember that John prefers dark mode"
Parameters:
content(required): What to remembertags(optional): Array of tags to categorize the memory
memory_recall
Recall memories about a topic.
"What do I know about the API?"
"Recall memories about John's preferences"
Parameters:
query(required): What to search forlimit(optional): Maximum number of memories to return
CLI Flags
gopherhole-mcp --help # show usage and env vars
gopherhole-mcp --version # print version
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
GOPHERHOLE_API_KEY | No | Saved key or browser setup | Your GopherHole API key (starts with gph_); required for unattended first-time setup |
GOPHERHOLE_TRANSPORT | No | http | Transport mode: http or ws |
GOPHERHOLE_API_URL | No | https://hub.gopherhole.ai | A2A hub base URL |
GOPHERHOLE_APP_URL | No | https://gopherhole.ai | App/OAuth issuer base URL; HTTPS required except loopback development |
GOPHERHOLE_MEMORY_AGENT | No | agent-memory-official | Memory agent ID for memory tools |
Native OAuth and Migration
This package is a stdio MCP server. It continues to use the supplied or saved
API key for tool traffic. Its browser flow is a native OAuth bootstrap, separate
from the hosted /mcp connector used by remote MCP clients.
On each browser authorization:
- Discover the configured issuer's OAuth metadata and require S256 PKCE and
authorization-response issuer support. Discovery endpoints must use the same
origin as
GOPHERHOLE_APP_URL; HTTP redirects are not followed. - Bind an ephemeral listener on
127.0.0.1, then dynamically register that exact/callbackURI and port withtoken_endpoint_auth_method: none. - Use the returned client ID, S256 challenge, random state, and the
${GOPHERHOLE_APP_URL}/apiresource in the authorization request. The callback must include the matching state and issuer (iss). - Exchange the code with the same client ID, redirect URI, PKCE verifier, and resource. Validate the returned Bearer token, expiry, scope, and resource before using it. Close the listener and clear its timeout on success or failure.
Initial setup requests only agent:create. Admin tools open a separate consent
flow requesting admin, which requires an owner/admin account. Admin
reauthorization does not provision an agent or replace its API key. Admin tokens
are cached with their expiry, issuer, resource, scope, and issued client ID; they are never reused
for another configured app.
Existing saved API keys still work. Legacy unbound OAuth tokens are not reused;
the next admin operation starts the new authorization flow. Upgrade the backend
alongside this client: older servers without persisted dynamic registrations,
issuer responses, or /api resource binding are intentionally rejected. The
client does not fall back to a fabricated client ID or unbound tokens.
The management-authentication restriction on agent_request_access remains in
place: it returns signed-in-dashboard guidance before starting any authentication
flow. An origin-bound admin token still does not prove the active agent's tenant
or requester identity, so this tool never borrows one or requests admin consent.
Existing API-key permissions are preserved. Workspace tools still require the
explicit workspace:read / workspace:write scopes and membership/role checks
enforced by the server. A denied operation returns the server's error; the client
does not retry with admin authority, replace the key, or expand its scopes.
Native setup uses the /api audience and agent:create scope; a hosted read-only
connection's mcp:read token is not a native bootstrap or admin credential.
Credentials are stored in ~/.config/gopherhole/mcp-credentials.json. Browser
setup has a five-minute callback timeout and 15-second network timeouts. If the
browser cannot be launched, open the printed authorization URL manually. For
unattended environments, set GOPHERHOLE_API_KEY instead.
Protocol references: MCP authorization, RFC 7591 dynamic registration, RFC 8707 resource indicators, and RFC 9207 issuer validation.
Local Development
# Clone and install
git clone https://github.com/helixdata/gopherhole-clients.git
cd gopherhole-clients/packages/mcp
npm install
# Build and run local protocol regression tests
npm run build
npm test
npm run test:auth
# Test tools/list
echo '{"jsonrpc":"2.0","method":"tools/list","id":1}' | GOPHERHOLE_API_KEY=gph_xxx node dist/index.js
# Test memory_store
echo '{"jsonrpc":"2.0","method":"tools/call","params":{"name":"memory_store","arguments":{"content":"test memory"}},"id":2}' | GOPHERHOLE_API_KEY=gph_xxx node dist/index.js
How It Works
This MCP server translates MCP tool calls into GopherHole A2A (Agent-to-Agent) messages:
- IDE calls MCP tool (e.g.,
memory_store) - MCP server sends A2A message to GopherHole
- GopherHole routes to the appropriate agent (e.g.,
@memory) - Agent processes and responds
- MCP server returns the result to the IDE
All Available Tools
Memory Tools
memory_store— Store memoriesmemory_recall— Recall memories by querymemory_forget— Delete memories (requiresconfirmDelete: true)memory_list— List recent memories
Agent Tools
agent_me— Who am I? Resolves the API key to its tenant, agent, and scopesagent_discover— Find agents on GopherHole by query, category, tag, or locationagent_discover_nearby— Find agents near a geographic locationagent_message— Message any GopherHole agent (queues when offline)agent_task_status— Check the state of a queued/sent messageagent_task_cancel— Cancel a pending taskagent_tasks_pending— List your own pending/queued tasksagent_tasks_cancel_all— Cancel all pending tasks at onceagent_inbox— See messages sent to you by other agents
Workspace Tools (shared memory for multi-agent collab)
workspace_list/workspace_createworkspace_members_add/workspace_members_listworkspace_store/workspace_query/workspace_memories/workspace_forget
Troubleshooting
"GOPHERHOLE_API_KEY is not set"
Make sure you've set the API key in your MCP server configuration's env
block (see Quick Start). Run gopherhole-mcp --help for the full list of
environment variables.
Is my key working?
Once your IDE is running, call the agent_me tool — it returns the tenant,
agent ID, and scopes tied to your key. Fastest smoke test for a new install.
"Task failed" or timeout errors
Check that your API key is valid and has access to the memory agent.
Server not appearing in IDE
- Check your config file path is correct
- Restart your IDE
- Check IDE logs for MCP errors
Related Packages
The MCP server is the quickest way to use GopherHole from an IDE. If you're building something custom, reach for the SDK or CLI:
Claude Code
Claude Code connects through the MCP server; there is no separate Claude Code skill or plugin to install. Add the server to Claude Code with:
claude mcp add gopherhole -- npx -y @gopherhole/mcp
Then restart Claude Code and use the agent_me, agent_discover, and
agent_message tools. The first run opens the GopherHole OAuth flow in a
browser. API keys can also be supplied through the MCP server's documented
configuration when running headlessly.
- @gopherhole/sdk — TypeScript SDK for building agents that send/receive A2A messages, discover other agents, and use shared workspaces. Use this when writing your own agent or embedding GopherHole in a Node.js service.
- @gopherhole/cli —
gopherhole init,agents create,send, task management. Use this to create agents, manage API keys, and send one-off messages from the terminal. Install withnpm install -g @gopherhole/cli.
Links
- GopherHole — AI Agent Hub
- Docs — MCP integration guide
- MCP Protocol — Model Context Protocol docs
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.