No install? Use cloud.anythingmcp.com directly.
Sign in, install the Folk in one click, paste the credentials, mint an MCP API key — done. No Docker, no git clone, no local server to run.
TL;DR
Drive Folk (modern relationship CRM) from any AI agent: people, companies, groups, deals, custom fields. 9 tools, Bearer auth.
💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Folk, paste your credentials, mint an MCP API key — done. No Docker, no
git clone, no local server.
Folk + Gemini
Drive Folk (modern relationship CRM) from any AI agent: people, companies, groups, deals, custom fields. 9 tools, Bearer auth.
Prerequisites
See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:
FOLK_API_TOKEN
Step 1 — Get credentials
folk.app).
Setup:
- Sign in to https://app.folk.app → bottom-left avatar → API & Integrations → API → Generate API token.
- Set
FOLK_API_TOKEN. - Note your workspace's groups — Folk's groups are loose collections (use them like tags).
Authentication: Authorization: Bearer ${FOLK_API_TOKEN}.
People / Companies / Deals: standard CRM objects, plus the relationship-graph idea — every person is linked to one or more companies, plus a free-form network of contacts.
Groups: flexible — Folk's primary segmentation. Add a person to multiple groups; each group has its own custom fields visible only when the person is in that group.
…(continued in the in-app connector instructions)
Step 2 — Install the adapter
git clone https://github.com/HelpCode-ai/anythingmcp.git
cd anythingmcp && docker compose up -d
Step 3 — Add the connector in Gemini
Gemini CLI reads MCP servers from ~/.gemini/settings.json (or %APPDATA%\gemini\settings.json on Windows). Add:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp",
"headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
}
}
}
- Get your MCP API key from AnythingMCP → Profile → MCP API Keys → New Key.
- Save the file and restart
gemini. - Run
/mcpinside the Gemini CLI —Folkshould be listed as available. - Vertex AI Studio: pass
https://cloud.anythingmcp.com/mcpto thetoolsarray of your request with the same Bearer header.
Available tools
| Tool | What it does |
|---|---|
folk_me | Return the user the token belongs to |
folk_list_people | List people with cursor pagination |
folk_get_person | Fetch a person by ID with full contact details + groups + companies |
folk_create_person | Create a person |
folk_update_person | Update a person (PATCH) |
folk_list_companies | List companies |
folk_create_company | Create a company |
folk_list_groups | List groups (collections) |
folk_list_group_custom_fields | List custom fields defined on a specific group |
FAQ
Does Gemini 1.5 Pro or 2.x support MCP? Yes — Gemini CLI ≥ 0.4 and Vertex AI tools API both accept MCP httpUrl connectors with Bearer headers.
Next steps
Was this guide helpful?