# Socrata Open Data MCP connector

The Socrata Open Data connector lets Claude, ChatGPT, Cursor, Microsoft Copilot and the Elaichi Agent search Socrata Open Data datasets and read their records, with every lookup running as the person who asked and written to an audit log.

Source: https://elaichi.ai/connectors/socrata/

## Facts

| | |
| --- | --- |
| Application | Socrata Open Data |
| Category | Database |
| AI tools | 3 |
| Authentication | Connects with an API key |
| Bring your own OAuth app | No |
| MCP endpoint | https://api.elaichi.ai/mcp |
| Works with | Claude, ChatGPT, Cursor, Microsoft Copilot, any MCP client, and the Elaichi Agent |
| Tools advertised by name | No. Connected tools are never listed one by one, however few there are. The endpoint advertises `search_tools` and `execute_tool` instead |

## What you can ask once Socrata Open Data is connected

- Which Socrata Open Data datasets cover building permits?
- Show the latest 311 service request records for this week's briefing.
- Open the budget dataset and list line items for Public Works.

## Connect Socrata Open Data in Elaichi

This happens once for the organization, before any client is involved.

1. Open Connections, choose Add connection, and pick Socrata Open Data.
2. Optionally set Share with, then press Connect.
3. Paste a Socrata Open Data API key. One person generates a token in Socrata Open Data and pastes it once. Everyone else works through Share with, and never sees it.

Credentials are vaulted and nobody, including the AI, reads them back. The connection becomes a toolbox immediately, so you can curate which Socrata Open Data tools are exposed, rename them, or freeze arguments before anyone points a client at it.

## Socrata Open Data MCP connector for Claude

Endpoint: https://api.elaichi.ai/mcp

1. Open Customize, then Connectors.
2. Press Add.
3. Name it, paste the MCP server URL, then Continue.
4. Sign in and approve.

On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.

## Socrata Open Data MCP connector for Claude Code

Endpoint: https://api.elaichi.ai/mcp

1. In a terminal, run `claude mcp add` with the endpoint.
2. Start Claude Code and run `/mcp`.
3. Pick elaichi, then sign in and approve in the browser.

```bash
claude mcp add --transport http elaichi --scope user https://api.elaichi.ai/mcp
```

Use `--scope project` instead to share it with the repository through `.mcp.json`.

## Socrata Open Data MCP connector for ChatGPT

Endpoint: https://api.elaichi.ai/mcp

1. Open Plugins, then press the + button.
2. Name it and paste the endpoint into Server URL.
3. Leave Authentication on OAuth, then tick the risk acknowledgement.
4. Press Create, then sign in and approve.

Works on the web. The plugin directory lives at chatgpt.com/plugins.

## Socrata Open Data MCP connector for Cursor

Endpoint: https://api.elaichi.ai/mcp

1. Open `~/.cursor/mcp.json`.
2. Add the endpoint under `mcpServers`.
3. Reload Cursor, then sign in and approve.

Set up per machine, so repeat it on each computer you work from.

## Socrata Open Data MCP connector for Microsoft Copilot

Endpoint: https://api.elaichi.ai/mcp

1. In Copilot Studio, open your agent, then Tools, Add a tool, New tool and Model Context Protocol.
2. Paste the endpoint into Server URL, choose OAuth 2.0, then Dynamic discovery, and press Create.
3. Create a new connection, sign in and approve, then press Add to agent.
4. Under Channels, open Teams and Microsoft Copilot and make the agent available in Microsoft Copilot.

Microsoft Copilot was called Microsoft 365 Copilot. Keep the tool on end-user credentials, so each person signs in as themselves.

## Connect Socrata Open Data to any MCP client

Endpoint: https://api.elaichi.ai/mcp

1. Add the endpoint as a remote MCP server.
2. Sign in and approve.

The Elaichi Agent already has these tools, with nothing to set up.

## What the consent screen decides

Every scope the client asks for starts ticked except "Delete things", which you tick yourself. Calling a Socrata Open Data tool needs "Use your connected apps". Over MCP there is no trusted place to confirm a write in the moment, so the consent screen is the standing approval rather than a formality. Think hard before granting Use your connected apps, which can also delete in connected apps and cannot be undone.

## What teams do with Socrata Open Data through Elaichi

### Pull the numbers for a briefing

Policy. Ask for the latest records in a Socrata Open Data dataset such as service requests or permits and get the figures you need for a council briefing without opening the portal.

### Find which datasets cover a topic

Research. Ask which Socrata Open Data datasets exist for housing, transit or public health and get a list with what each one holds before you start an analysis.

### Check a figure before it goes out

Communications. Before a press release or social post, confirm a number against the published Socrata Open Data records so the statement matches what the public can see.

### Compare records across neighborhoods

Planning. Read building permit or inspection records from Socrata Open Data and have the agent group them by district or month for a planning review.

### Read published budget line items

Finance. Open a Socrata Open Data budget dataset by its ID and ask for the line items behind a department total when a question comes in.

### Watch a dataset for new records

Operations. Ask what has been added to a Socrata Open Data dataset since last week, such as new service requests or closures, and summarize it for the team.

## Elaichi vs Zapier MCP vs Composio for Socrata Open Data

All three can connect Socrata Open Data to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.

| What to check | Elaichi | Zapier MCP | Composio |
| --- | --- | --- | --- |
| Where the AI connects | One address for the whole organization. Endpoint: https://api.elaichi.ai/mcp | A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over Socrata Open Data tools | Allow or restrict single Socrata Open Data tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per Socrata Open Data call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | Free for one person; $15 per user per month on Gold. | 2 tasks per successful call. | Billed per tool call. |

Sources: Zapier MCP [docs](https://docs.zapier.com/mcp/get-started/quickstart), [security](https://docs.zapier.com/mcp/manage/security), [usage](https://docs.zapier.com/mcp/features/usage); Composio [docs](https://docs.composio.dev/docs/composio-connect), [gateway](https://composio.dev/mcp-gateway), [enterprise](https://composio.dev/enterprise), [pricing](https://composio.dev/pricing). Checked September 2026.

Longer take: [Zapier MCP alternative](/blog/zapier-mcp-alternative/) and [when you don't need an MCP gateway](/blog/when-you-dont-need-an-mcp-gateway/).

## Frequently asked questions

### How do I connect Socrata Open Data to Claude?

In Elaichi, add the Socrata Open Data connector and paste in the API key from your Socrata account, there is no OAuth application to register and no client ID or secret to generate. Then in Claude open Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Sign in to Elaichi when Claude asks and Socrata Open Data datasets are available in your next conversation.

### Does Socrata Open Data work with ChatGPT and Cursor as well as Claude?

Yes. Once Socrata Open Data is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, Microsoft Copilot, any MCP client and the Elaichi Agent. You connect Socrata Open Data once and every client sees the same datasets under the same rules.

### What can an AI agent actually do with my Socrata Open Data data?

An agent can list the datasets available on your Socrata Open Data portal, open a specific dataset by its ID to see what it contains, and read the records inside it. In practice that means asking for the latest permit records, finding which datasets cover transit, or pulling budget line items for a question. Short, concrete asks such as naming the dataset and the month tend to work better than long sentences.

### Does connecting Socrata Open Data give the AI every dataset on the portal?

It gives the AI exactly what the API key used to connect Socrata Open Data can already see, and nothing more. Elaichi can narrow that further by role or by person so a team only reaches certain datasets, but it can never widen access beyond what Socrata Open Data itself allows.

### Can my team share one Socrata Open Data connection?

Yes. One person connects Socrata Open Data in Elaichi and shares the connection with a team, and nobody else ever handles the API key. Each teammate still signs in to Elaichi as themselves, so the audit log names the person who read each dataset, not the account that was connected.

### Can I stop an agent from deleting or changing things in Socrata Open Data?

The Socrata Open Data connector only lists datasets and reads records, so nothing can be deleted or changed through it. Even so, each action can be restricted for a role or for one person in Elaichi, for example to keep a group from opening certain datasets. A restricted action still appears in Elaichi's tool search, flagged as restricted, but no client can run it, whatever the prompt says.

### What happens to a Socrata Open Data connection when someone leaves?

When a person is offboarded in Elaichi, their access to Socrata Open Data through Elaichi ends at once, in every client. A shared Socrata Open Data connection keeps working for everyone else on the team. If you ever want to remove Socrata Open Data entirely, disconnecting it once in Elaichi removes it from Claude, ChatGPT, Cursor, Microsoft Copilot and every other client at the same time.

### Does the Socrata Open Data MCP connector work with Gemini, Codex, Claude Code or other MCP clients?

Yes. Socrata Open Data is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, Microsoft Copilot, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.

### Is Elaichi an alternative to Zapier MCP for Socrata Open Data?

Yes. Both let Claude, ChatGPT or Cursor use Socrata Open Data. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Socrata Open Data call.

### How is Elaichi different from Composio for Socrata Open Data?

Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Socrata Open Data: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.

## All 3 Socrata Open Data tools

Every tool below is callable through https://api.elaichi.ai/mcp once Socrata Open Data is connected, subject to the toolbox it is in and the restrictions on the caller.

- **List all Socrata Open Data records** (List). List rows of one Socrata dataset by dataset_id. Pass a small limit (10-50; the default is 1000 rows) and select only the columns you need. where, select, q and order map to SoQL, e.g. where=county='Monroe'. Other parameters are exact-match column filters. For counts, pass select=count(*) and order=count(*).
- **List all Socrata Open Data datasets** (List). Search the datasets published on the connected portal (Socrata Discovery API). Use q to search by name or topic and a small limit (10 to 25). Each item's resource.id is the dataset_id for the records tool, and resource.columns_field_name lists its column names.
- **Get single Socrata Open Data dataset by ID** (Get). Get one dataset's metadata by its 4x4 id (e.g. vn5v-hh5r): name, description, when its rows were last updated, and its columns. Use columns[].fieldName as the names in the records tool's select, where and order.
