# Pydantic Logfire MCP connector

Connect Pydantic Logfire to Elaichi and Claude, ChatGPT, Cursor and the Elaichi Agent can query your traces with SQL, surface recent exceptions and manage dashboards, alerts and issues, each person signed in as themselves.

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

## Facts

| | |
| --- | --- |
| Application | Pydantic Logfire |
| Category | Observability |
| Authentication | Connects over OAuth |
| Bring your own OAuth app | No |
| Native MCP | Yes. Pydantic Logfire builds and runs this MCP server. Elaichi adds sign-in, access controls and an audit log on top |
| Support for its tools | pydantic.dev/contact |
| MCP endpoint | https://api.elaichi.ai/mcp |
| Works with | Claude, ChatGPT, Cursor, 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 Pydantic Logfire is connected

- Show me the exceptions from the last hour in the checkout service.
- Which alerts fired overnight and are any still open?
- Create a dashboard tracking p95 latency for the payments API.

## Connect Pydantic Logfire in Elaichi

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

1. Open Connections, choose Add connection, and pick Pydantic Logfire.
2. Optionally set Share with, then press Connect.
3. Approve it in Pydantic Logfire. Pydantic Logfire's own window opens. Whoever approves it decides what this connection can reach.

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

## Pydantic Logfire 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.

## Pydantic Logfire 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 today. The plugin directory lives at chatgpt.com/plugins.

## Pydantic Logfire 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.

## Connect Pydantic Logfire 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

Only Read is granted by default, which is not enough to call a Pydantic Logfire tool. 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. Grant Read and Run tools. Think hard before granting Delete, which reaches into connected apps and cannot be undone.

## What teams do with Pydantic Logfire through Elaichi

### Find out what broke after a deploy

Engineering. Ask which services started throwing exceptions in the last hour and get the stack traces back in the chat. Then open an issue in Pydantic Logfire for the one that matters without leaving the conversation.

### Triage alerts before the standup

On-call. Ask which alerts fired overnight, which are still open and what each one points at. Close the noisy ones and leave a note on the rest so the next person knows where things stand.

### Build a dashboard from a plain question

Platform. Describe the dashboard you want, say p95 latency per endpoint for the payments service, and have it created in Pydantic Logfire. Adjust the panels by asking rather than by clicking through settings.

### Check a customer's error before replying

Support. Paste a customer's request ID and ask what happened to that trace. The agent pulls the spans and exceptions so the reply to the customer is accurate the first time.

### Measure how a feature is behaving

Product. Ask how often a new endpoint was called this week and how slow the worst requests were. The answer comes from a SQL query over your spans, not from a guess.

### Run SQL over telemetry without the console

Data. Ask for error counts by service and day, or the slowest queries this month, and have the SQL written and run against Pydantic Logfire for you. Refine the question and run it again.

## Elaichi vs Zapier MCP vs Composio for Pydantic Logfire

All three can connect Pydantic Logfire 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 Pydantic Logfire tools | Allow or restrict single Pydantic Logfire 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 Pydantic Logfire 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 | $15 per user per month. | 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 Pydantic Logfire to Claude?

Connect Pydantic Logfire in Elaichi first, which means signing in to Pydantic Logfire over OAuth in your browser, with 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 as the endpoint. Claude signs you in to Elaichi and your Pydantic Logfire tools are available in the next chat.

### Does Pydantic Logfire work with ChatGPT and Cursor as well as Claude?

Yes. Pydantic Logfire is connected once in Elaichi, and the same endpoint, https://api.elaichi.ai/mcp, is added to Claude, ChatGPT, Cursor or any other MCP client. The Elaichi Agent uses it as well, so there is nothing separate to set up per client.

### What can an AI agent actually do with my Pydantic Logfire data?

It can run SQL against your Pydantic Logfire spans and traces, pull up recent exceptions with their stack traces, and create or change dashboards, alerts and issues. In practice that means asking what broke in the last hour, which alerts are still open, or how slow an endpoint was this week. Short concrete asks work better than long paragraphs, so name the service or the time window you care about.

### Does connecting Pydantic Logfire give the AI access to every project?

No. Every call to Pydantic Logfire runs as the person who signed in, so the agent sees the projects and organizations that person can already open and nothing more. Elaichi can narrow that further with restrictions per action, and it can never widen it beyond what Pydantic Logfire itself allows.

### Can my team share one Pydantic Logfire connection?

Yes. One person connects Pydantic Logfire in Elaichi and shares it with a team, and nobody else ever handles a token or signs in to Pydantic Logfire to set it up. Each teammate still signs in to Elaichi as themselves, so the audit log names the individual who ran a query or closed an issue.

### Can I stop an agent from deleting or changing things in Pydantic Logfire?

Yes. Restrictions in Elaichi work per action, so you can allow reading spans and exceptions while blocking changes to dashboards, alerts or issues in Pydantic Logfire. A restricted action is never advertised to Claude, ChatGPT or Cursor at all, so no prompt, however it is worded, can reach it.

### What happens to a Pydantic Logfire connection when someone leaves?

Offboarding that person in Elaichi ends their access to Pydantic Logfire through every client at once. A shared Pydantic Logfire connection keeps working for everyone else on the team. If you want the connection gone entirely, disconnecting it once in Elaichi removes it from Claude, ChatGPT, Cursor and the Elaichi Agent together.

### Does the Pydantic Logfire MCP connector work with Gemini, Codex, Claude Code or other MCP clients?

Yes. Pydantic Logfire 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, 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 Pydantic Logfire?

Yes. Both let Claude, ChatGPT or Cursor use Pydantic Logfire. 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 Pydantic Logfire call.

### How is Elaichi different from Composio for Pydantic Logfire?

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 Pydantic Logfire: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.