MCP server
by picahq
Pica is automated workflow software for business process automation, integrating actions across services via a unified i
Integrates with 200+ third-party services through a unified API platform, allowing you to execute actions and automate workflows without managing individual API keys.
Pica is an official MCP server published by picahq that provides AI assistants with tools and capabilities via the Model Context Protocol. Pica is automated workflow software for business process automation, integrating actions across services via a unified i It is categorized under developer tools.
You can install Pica in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
MIT
Pica is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
Add new capabilities to Claude beyond text generation
Example
Access external data sources, execute code, interact with tools and services
Transform Claude from chatbot to action-taking agent
Provide Claude with access to relevant context and data
Example
Load project documentation, access knowledge bases, query databases
Get more accurate, context-aware responses
Automate multi-step workflows combining AI and external tools
Example
Research → Summarize → Create document → Send notification
Complete complex tasks end-to-end without manual steps
Share your MCP server with the developer community
Pica is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.
Pica is among the better-indexed MCP projects we tried; the explainx.ai summary tracks the official description.
Pica has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.
Pica has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.
We wired Pica into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
We evaluated Pica against two servers with overlapping tools; this profile had the clearer scope statement.
Pica reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
Pica reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
We wired Pica into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
We wired Pica into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
showing 1-10 of 69
A Model Context Protocol (MCP) server that integrates with Pica, enabling seamless interaction with various third-party services through a standardized interface. This server provides direct access to platform integrations, actions, execution capabilities, and robust code generation capabilities.
The fastest way to get up and running is with the Pica CLI. It handles API key configuration and MCP installation for your agent or editor of choice.
npm install -g @picahq/cli
pica init
pica init will prompt you for your API key (get one from the Pica dashboard) and walk you through configuring the MCP server for your environment (Claude Desktop, Cursor, Claude Code, etc.).
If you prefer to configure the server manually, install the package directly:
npm install @picahq/mcp
Then set the required environment variable:
PICA_SECRET=your-pica-secret-key
You can scope connections to a specific identity (e.g., a user, team, or organization) by setting these optional environment variables:
PICA_IDENTITY=user_123
PICA_IDENTITY_TYPE=user
| Variable | Description | Values |
|---|---|---|
PICA_IDENTITY | The identifier for the entity (e.g., user ID, team ID) | Any string |
PICA_IDENTITY_TYPE | The type of identity | user, team, organization, project |
When set, the MCP server will only return connections associated with the specified identity. This is useful for multi-tenant applications where you want to scope integrations to specific users or entities.
Fine-tune what the MCP server can see and do by setting these optional environment variables:
PICA_PERMISSIONS=read
PICA_CONNECTION_KEYS=conn_key_1,conn_key_2
PICA_ACTION_IDS=action_id_1,action_id_2
PICA_KNOWLEDGE_AGENT=true
| Variable | Type | Default | Description |
|---|---|---|---|
PICA_PERMISSIONS | read | write | admin | admin | Filter actions by HTTP method. read = GET only, write = GET/POST/PUT/PATCH, admin = all methods |
PICA_CONNECTION_KEYS | * or comma-separated keys | * | Restrict visible connections and platforms to specific connection keys |
PICA_ACTION_IDS | * or comma-separated IDs | * | Restrict visible and executable actions to specific action IDs |
PICA_KNOWLEDGE_AGENT | true | false | false | Remove the execute_pica_action tool entirely, forcing knowledge-only mode |
All defaults preserve current behavior. If no access control env vars are set, the server starts with full access and all tools available.
If you used pica init, the configuration below is already done for you. These examples are for reference or manual setups.
npx @picahq/mcp
On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"pica": {
"command": "npx",
"args": ["@picahq/mcp"],
"env": {
"PICA_SECRET": "your-pica-secret-key"
}
}
}
}
In the Cursor menu, select "MCP Settings" and add the following:
{
"mcpServers": {
"pica": {
"command": "npx",
"args": ["@picahq/mcp"],
"env": {
"PICA_SECRET": "your-pica-secret-key"
}
}
}
}
The remote MCP server is available at https://mcp.picaos.com.
docker build -t pica-mcp-server .
docker run -e PICA_SECRET=your_pica_secret_key pica-mcp-server
All environment variables listed in the Setup section can be passed as -e flags.
Build Email Form:
"Create me a React form component that can send emails using Gmail using Pica"
Linear Dashboard:
"Create a dashboard that displays Linear users and their assigned projects with filtering options using Pica"
QuickBooks Table:
"Build a paginatable table component that fetches and displays QuickBooks invoices with search and sort using Pica"
Slack Integration:
"Create a page with a form that can post messages to multiple Slack channels with message scheduling using Pica"
Gmail Example:
"Get my last 5 emails from Gmail using Pica"
Slack Example:
"Send a slack message to #general channel: 'Meeting in 10 minutes' using Pica"
Shopify Example:
"Get all products from my Shopify store using Pica"
All tool inputs are validated against Zod schemas before execution. Path variables are checked for completeness; missing or empty values throw descriptive errors rather than producing malformed requests. API failures from upstream platforms are caught and returned as structured MCP error responses with actionable messages. The server never surfaces raw stack traces to clients.
All requests to third-party platforms are authenticated and proxied through Pica's API. The MCP server never handles OAuth tokens or platform API keys directly. The PICA_SECRET key is the sole credential required, and it is automatically redacted from all response payloads returned to clients. Sensitive headers are stripped from logged and returned request configurations.
For fine-grained control, the server supports permission levels (PICA_PERMISSIONS), connection key scoping (PICA_CONNECTION_KEYS), action allowlisting (PICA_ACTION_IDS), and a knowledge-only mode (PICA_KNOWLEDGE_AGENT) that removes execution capabilities entirely. See the Access Control section above for details.
MIT
For support, please contact support@picaos.com or visit https://picaos.com
Prerequisites
Time Estimate
15-60 minutes depending on server complexity
Steps
Troubleshooting
✓ Do
✗ Don't
💡 Pro Tips
Architecture
Model Context Protocol standardizes how AI hosts (Claude, Cursor) communicate with external tools and data sources through server implementations.
Protocols
Compatibility
✓ Use when
Use when you need Claude to access external data, execute actions, or integrate with tools. Best for extending AI capabilities beyond conversation.
✗ Avoid when
Avoid when native integrations exist (use official APIs directly), for real-time critical systems, or when security/compliance requires zero external dependencies.