Cantrip

io.github.oztenPublished by GitHub account oztenv1.0.5Updated Oct 24, 2026

MCP server for Cantrip — AI-powered GTM engine for solo founders

VerifiedSTDIODesktop onlyProductivity & WorkflowBusiness & Commerce

Overview

AI-generated overview

Cantrip is a local MCP server that gives an assistant structured go-to-market workflows for finding a product's first customers.

What you can do
Cantrip exposes 17 tools covering setup, core commands, review, and generic entity CRUD. An assistant can initialize or connect a project, take a project snapshot, list gap-analysis opportunities, generate context-rich prompts, spawn background agents, and query an audit trail. It can also list, accept, reject, resolve, or dismiss inferred entities and escalations, and create or edit entities such as ICPs, pain points, value props, experiments, channels, competitors, and contacts.
When to use it
Use it when a solo or technical founder wants an assistant to help define an ideal customer profile, research competitors, and turn gap analysis into concrete next actions and a short GTM plan. It suits users who already work in an MCP-compatible agent and want that work tracked in a Cantrip project.
Requirements
Runs locally over stdio via the npm package mcp-server-cantrip, so Node.js and npx are needed. A Cantrip API key is required in the CANTRIP_API_KEY environment variable, obtained from the Cantrip settings page. The server needs network access to the Cantrip API. Desktop only; no web executable.
Before you install
The server requires the secret CANTRIP_API_KEY, which is placed in the MCP client config; anyone with access to that file can read it. Tool calls are sent over HTTPS to the Cantrip API, so project data leaves the machine. Several tools write or change data, including creating and editing entities, accepting or rejecting inferred entities, resolving escalations, and spawning background agents. The README notes that without the -y flag npx can hang over stdio.

Installation

In SourceWeft

  1. Open Cantrip in the dashboard and add it to a workspace.
  2. 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

mcp-server-cantrip

Cantrip helps technical founders find their first customers with structured GTM workflows.

  • Nail your ICP — define ideal customer profiles, buyer pains, and value props
  • Research competitors — map the landscape and find where you can win
  • Get next actions — gap analysis tells you exactly what to work on, then does it for you

Works with Claude Code / Claude Desktop / Cursor — any MCP-compatible agent.

Quick start

  1. Get your API key at cantrip.ai (settings)
  2. Add the server:
bash
claude mcp add cantrip -e CANTRIP_API_KEY=your-api-key -- npx -y mcp-server-cantrip
  1. Try this prompt:

"Initialize a Cantrip project for my product: [describe yours in one sentence]"

Configuration

The Quick start command above covers Claude Code. Verify it worked with claude mcp list or the /mcp command inside a session.

Claude Desktop / Cursor / manual JSON

All MCP clients use the same JSON block. Add it to the appropriate config file:

ClientConfig file
Claude Code (manual)~/.claude.json
Claude Code (project-scoped).mcp.json in project root
Claude Desktop (macOS)~/Library/Application Support/Claude/claude_desktop_config.json
Claude Desktop (Windows)%APPDATA%\Claude\claude_desktop_config.json
Cursor.cursor/mcp.json (project) or ~/.cursor/mcp.json (global)
json
{  "mcpServers": {    "cantrip": {      "command": "npx",      "args": ["-y", "mcp-server-cantrip"],      "env": {        "CANTRIP_API_KEY": "your-api-key"      }    }  }}

Note: The -y flag is required — without it, npx prompts for confirmation which hangs over stdio.

Windows (not WSL): Use "command": "cmd" with "args": ["/c", "npx", "-y", "mcp-server-cantrip"].

Project-scoped with teams: Use "${CANTRIP_API_KEY}" in the env value so each developer sets the key in their shell profile.

Project Context (.cantrip.json)

Each project directory contains a .cantrip.json file that tells Cantrip which project to target:

json
{  "project": "my-saas"}

This file is created automatically by cantrip_init (new project) or cantrip_connect (existing project). The agent manages it — you don't need to create it manually.

Multiple projects on the same machine? Each project directory gets its own .cantrip.json. The agent switches context by working in the right directory.

Examples of How to use Cantrip

After connecting Cantrip, try these prompts in order:

  1. "Initialize a Cantrip project for my product: [one sentence about what you're building]"
  2. "Find my likely ICP and top 3 buyer pains."
  3. "Research 5 competitors and tell me where I can win."
  4. "Give me a one-week GTM plan."

Troubleshooting

Server not found / no tools appear:

  • Run claude mcp list (Claude Code) or /mcp inside a session to check connection status.
  • Make sure the config is in the right file — Claude Code uses ~/.claude.json or .mcp.json, not ~/.claude/mcp.json.

Server hangs on startup:

  • Ensure you have -y in the npx args. Without it, npx waits for interactive confirmation that can never arrive over stdio.

"Cannot reach Cantrip API" errors:

  • Verify CANTRIP_API_KEY is set in the env block of your MCP config.
  • Check that https://api.cantrip.ai is reachable from your network.

Windows "Connection closed" errors:

  • Use "command": "cmd" with "args": ["/c", "npx", "-y", "mcp-server-cantrip"].

Architecture

Agent (Claude, etc.) ── MCP protocol (stdio) ──> mcp-server-cantrip ── HTTPS POST ──> https://api.cantrip.ai

The MCP server is a thin translation layer. It converts MCP tool calls into {command, args, flags} JSON envelopes and POSTs them to the Cantrip API. Zero business logic — identical contract to the CLI and React UI.

Tools (17)

Setup

ToolDescription
cantrip_connectConnect workspace to a project (reads/writes .cantrip.json)
cantrip_statusCheck if the daemon is running
cantrip_initCreate a new project and auto-connect

Core Commands

ToolDescription
cantrip_snapshotProject overview, drill into entity types
cantrip_nextList gap-analysis opportunities
cantrip_next_promptGenerate a context-rich LLM prompt for an opportunity
cantrip_next_runSpawn a background agent for an opportunity
cantrip_historyQuery the audit trail

Review

ToolDescription
cantrip_reviewList items pending review
cantrip_review_acceptAccept an inferred entity
cantrip_review_rejectReject an inferred entity
cantrip_review_resolveResolve an escalation
cantrip_review_dismissDismiss an escalation

Entity CRUD (generic)

ToolDescription
cantrip_entity_listList entities of a type
cantrip_entity_showShow entity detail
cantrip_entity_addCreate a new entity
cantrip_entity_editEdit an existing entity

Supported entity types: icp, pain_point, value_prop, experiment, channel, competitor, contact

License

MIT

Source: README.md at commit b25ddc6

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.5LatestSep 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