> **Building with AI coding agents?** Install the authstack plugin with one command. This equips your agent with accurate Scalekit implementation patterns.
>
> **Recommended** (the `-y` flags skip prompts, so the command runs without an interactive terminal):
> ```bash
> npx -y @scalekit-inc/cli setup -y
> ```
>
> Global:
> ```bash
> npm install -g @scalekit-inc/cli
> scalekit setup -y
> ```
>
> Supports Claude Code, Cursor, GitHub Copilot, Codex + skills for other Agent Skills-compatible agents in `~/.agents/skills`.
> Skills: integrate-agentkit, implement-saaskit, add-mcp-oauth, implement-sso, implement-scim.
> [Full setup guide](https://docs.scalekit.com/dev-kit/build-with-ai/)

---

# Connect AI agents to the Candid MCP server

The Candid MCP connector routes your AI agent's tool calls to Candid's own MCP server through Scalekit. Each user signs in to Candid once, and Scalekit stores and refreshes their tokens, so your agent never handles credentials. It comes with 6 tools.

**Authentication:** OAuth 2.1/DCR
**Categories:** Search, AI
**Tools:** 6: 6 read, 0 write, 0 destructive
**Users sign in with:** OAuth
**OAuth app:** Scalekit's or your own
**Built by:** Vendor MCP
**Try it:** [Playground in the Scalekit dashboard](https://app.scalekit.com/ws/signup?sk_intent=playground&provider=CANDIDMCP)

## What you can do

- **Search nonprofits and funders**: find nonprofits and grantmaking organizations by name, mission, location, or type of work
- **Search sector research**: find articles, research reports, and training content about the social and philanthropic sector
- **Identify organizations and places**: resolve nonprofit names in text to Candid profiles and place names to location IDs
- **Classify by subject**: tag text with philanthropy subject and population codes from Candid's taxonomy

## Setup

1. ### Install the SDK

   **Node.js**

   ```bash
   npm install @scalekit-sdk/node dotenv
   ```

   **Python**

   ```bash
   pip install scalekit-sdk-python python-dotenv
   ```

2. ### Set your credentials

   Add your Scalekit credentials to your `.env` file. Find values in **[app.scalekit.com](https://app.scalekit.com)** > **Developers** > **API Credentials**.

   ```sh title=".env"
   SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
   SCALEKIT_CLIENT_ID=<your-client-id>
   SCALEKIT_CLIENT_SECRET=<your-client-secret>
   ```

3. ### Create the Candid MCP connection

   In **AgentKit > Connections**, create a Candid MCP connection. The name you give it is the `connection_name` your code passes. See [Configure connections](/agentkit/connections/).

   Scalekit credentials are available for Candid MCP server, so you don't need to register an OAuth app.

4. ### Authorize a user and make your first call

   **Node.js** (`quickstart.mts`)

   ```typescript
   import { ScalekitClient } from '@scalekit-sdk/node'
   import 'dotenv/config'
   import { createInterface } from 'node:readline/promises'

   const scalekit = new ScalekitClient(
     process.env.SCALEKIT_ENVIRONMENT_URL,
     process.env.SCALEKIT_CLIENT_ID,
     process.env.SCALEKIT_CLIENT_SECRET,
   )
   const actions = scalekit.actions

   const connector = 'candidmcp'
   const identifier = 'user_123'

   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize Candid MCP:', link)
   const rl = createInterface({ input: process.stdin, output: process.stdout })
   await rl.question('Press Enter after authorizing...')
   rl.close()

   // Make your first call
   const result = await actions.executeTool({
     connector,
     identifier,
     toolName: 'candidmcp_current_date',
     toolInput: {},
   })
   console.log(result)
   ```

   ```bash
   npx tsx quickstart.mts
   ```

   **Python** (`quickstart.py`)

   ```python
   import os
   from scalekit import ScalekitClient
   from dotenv import load_dotenv
   load_dotenv()

   scalekit_client = ScalekitClient(
       env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"),
       client_id=os.getenv("SCALEKIT_CLIENT_ID"),
       client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),
   )
   actions = scalekit_client.actions

   connection_name = "candidmcp"
   identifier = "user_123"

   # Generate an authorization link for the user
   link_response = actions.get_authorization_link(
       connection_name=connection_name,
       identifier=identifier,
   )
   print("Authorize Candid MCP:", link_response.link)
   input("Press Enter after authorizing...")

   # Make your first call
   result = actions.execute_tool(
       tool_input={},
       tool_name="candidmcp_current_date",
       connection_name=connection_name,
       identifier=identifier,
   )
   print(result)
   ```

   ```bash
   python quickstart.py
   ```

   Each user signs in once. See [Authorize a user](/agentkit/tools/authorize/) for the full flow and statuses.

## Tools

Pass the exact name to `execute_tool`, with an input like each tool's example. To ask for a tool that's missing, use the [request form](https://scalekitsupport.portal.usepylon.com/forms/request-a-connector-tool).

**Node.js**

```typescript
const result = await actions.executeTool({
  toolName: 'candidmcp_current_date',
  toolInput: {},
  connector: 'candidmcp',
  identifier: 'user_123',
})
```

**Python**

```python
result = actions.execute_tool(
    tool_name="candidmcp_current_date",
    tool_input={},
    connection_name="candidmcp",
    identifier="user_123",
)
```

`result.data` is the app's response as JSON, and `result.execution_id` (`executionId` in Node.js) is the ID of the call.

### `candidmcp_current_date`

Current Date · Read-only

Get today's date for use in time-sensitive queries and data requests.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs: none.

Example input: `{}`

### `candidmcp_identify_locations`

Identify Locations · Read-only

Detect and resolve geographic names in text to Geonames IDs for use in organization search filters.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `text` (`string`, required): No description.

Example input: `{"text":"<text>"}`

### `candidmcp_identify_mentioned_organizations`

Identify Mentioned Organizations · Read-only

Resolve nonprofit names mentioned in text to Candid profile URLs.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `organizations` (`array`, required): No description.

Example input: `{"organizations":[]}`

### `candidmcp_knowledge_resources`

Knowledge Resources · Read-only

Search Candid's knowledge base for articles, blog posts, research reports, and training content about the social and philanthropic sector.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `query` (`string`, required): No description.
- `sources` (`array`, required): No description.
- `news_days_ago` (`integer`, optional): No description. Default: `60`.

Example input: `{"query":"<query>","sources":[]}`

### `candidmcp_search_organizations`

Search Organizations · Read-only

Search Candid's database for nonprofits and grantmaking organizations by name, mission, location, or type of work.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `query` (`string`, required): No description.
- `geonameids_of_geographies_served` (`string`, optional): No description.
- `geonameids_of_organization_location` (`string`, optional): No description.
- `leader_demographics` (`string`, optional): No description.
- `located_admin1` (`string`, optional): No description.
- `located_postal_code` (`string`, optional): No description.
- `org_seal_status` (`string`, optional): No description.
- `populations_served_codes` (`string`, optional): No description.
- `subject_codes` (`string`, optional): No description.

Example input: `{"query":"<query>"}`

### `candidmcp_taxonomy_terms`

Taxonomy Terms · Read-only

Classify text using Candid's Philanthropy Classification System (PCS) taxonomy to get subject and population codes.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `text` (`string`, required): No description.

Example input: `{"text":"<text>"}`

## Related

Other Search connectors ([all 36](/agentkit/connectors/?category=search)):

- [Supadata](/agentkit/connectors/supadata/): Scalekit connector, API key, 21 tools
- [Exa](/agentkit/connectors/exa/): Scalekit connector, API key, 21 tools
- [Brave Search](/agentkit/connectors/brave/): Scalekit connector, API key, 18 tools


---

## More Scalekit documentation

| Resource | What it contains | When to use it |
|----------|-----------------|----------------|
| [/llms.txt](/llms.txt) | Structured index with routing hints per product area | Start here — find which documentation set covers your topic before loading full content |
| [/llms-full.txt](/llms-full.txt) | Complete documentation for all Scalekit products in one file | Use when you need exhaustive context across multiple products or when the topic spans several areas |
| [sitemap-0.xml](https://docs.scalekit.com/sitemap-0.xml) | Full URL list of every documentation page | Use to discover specific page URLs you can fetch for targeted, page-level answers |