Pydantic Logfire (EU) MCP connector
Connecting Pydantic Logfire (EU) to Elaichi lets Claude, ChatGPT, Cursor and the Elaichi Agent query your telemetry with SQL, surface recent exceptions, and manage dashboards, alerts and issues, all inside each person's own access.
-
How it connects. Connects over OAuth. The credential goes into a vault nobody reads back.
-
One address. https://api.elaichi.ai/mcp, the same for every user.
-
Their own access. An agent never gets more than the person it acts for.
How to connect
How to connect Pydantic Logfire (EU) to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect Pydantic Logfire (EU) once
-
Open Connections, choose Add connection, and pick Pydantic Logfire (EU).
-
Optionally set Share with to give a team access, then press Connect.
-
Approve it in Pydantic Logfire (EU). Pydantic Logfire (EU)'s own window opens. Whoever approves it decides what this connection can reach.
The credential is vaulted. Nobody reads it back, not even the AI.
Add connection
Choose a connector.
In your AI client
Point it at one endpoint
Everyone in the organization uses the same address, and each person only ever reaches what their own account allows.
Pydantic Logfire (EU) MCP connector for Claude
-
1
Open Customize, then Connectors.
-
2
Press Add.
-
3
Name it, paste the MCP server URL, then Continue.
https://api.elaichi.ai/mcp -
4
Sign in and approve.
On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.
Pydantic Logfire (EU) MCP connector for ChatGPT
-
1
Open Plugins, then press the + button.
-
2
Name it and paste the endpoint into Server URL.
https://api.elaichi.ai/mcp -
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 (EU) MCP connector for Cursor
-
1
Open
~/.cursor/mcp.json. -
2
Add the endpoint under
mcpServers.https://api.elaichi.ai/mcp -
3
Reload Cursor, then sign in and approve.
~/.cursor/mcp.json
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
Set up per machine, so repeat it on each computer you work from.
Connect Pydantic Logfire (EU) to any MCP client
-
1
Add the endpoint as a remote MCP server.
https://api.elaichi.ai/mcp -
2
Sign in and approve.
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
The Elaichi Agent already has these tools, with nothing to set up.
Use cases
What teams do with Pydantic Logfire (EU) through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Engineering
Find out why last night's deploy got noisy
Ask which exceptions started appearing after the release and get the matching traces with their error messages, without writing the SQL yourself.
-
On-call
Triage an alert before paging anyone else
When an alert fires, ask what it is watching, which service tripped it, and whether the same issue was already open last week.
-
Support
Check a customer's failed request
Give the agent a request ID or a customer email and get back the trace, the error and the time it happened, in plain language.
-
Platform
Keep dashboards in step with new services
Ask the agent to add a panel for a newly deployed service or copy a dashboard layout for a second environment.
-
Product
Get a weekly read on endpoint usage
Ask how often a new endpoint was hit this week and how that compares to last week, pulled straight from telemetry.
-
QA
Close out issues that stopped reproducing
Ask which open issues have not recurred in seven days and close them with a note, so the issue list stays honest.
Try asking
- “Show exceptions in the checkout service from the last hour”
- “Which alerts fired overnight and are any still open?”
- “Add a p95 latency panel to the API dashboard”
Compare
Elaichi vs Zapier MCP vs Composio for Pydantic Logfire (EU)
All three can connect Pydantic Logfire (EU) 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.
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 (EU) tools | Allow or restrict single Pydantic Logfire (EU) 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 (EU) 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, security, usage; Composio docs, gateway, enterprise, pricing. Checked September 2026.
Longer take: Zapier MCP alternative and when you don't need an MCP gateway.
See it in Elaichi
What connecting Pydantic Logfire (EU) gets you
5 screens from the product, each doing one job for your Pydantic Logfire (EU) account.
The agent
Ask what broke, get the trace back.
Three starter prompts query live Pydantic Logfire (EU) telemetry and answer in plain language.
- traces
- exceptions
- dashboards
- alerts
Ask Elaichi to work across your apps.
Show exceptions in the checkout service from the last hour
Which alerts fired overnight and are any still open?
Add a p95 latency panel to the API dashboard
Also runs in Claude, ChatGPT or Cursor
MCP clients
One endpoint, every client, no shared key.
Claude, ChatGPT and Cursor reach Pydantic Logfire (EU) through one governed org endpoint over OAuth.
Copy the endpoint
Toolboxes
Each team gets its own toolbox.
Scope Pydantic Logfire (EU) toolboxes to on-call, platform and support, each seeing only its share.
- Engineering
- On-call
- Platform
- Support
Shared connections
Teammates work through it, never see the token.
One person connects Pydantic Logfire (EU) and shares it with teams, no credential changes hands.
- Production
- Staging
- On-call
- Platform
Audit log
Every query has a name on it.
Who ran which SQL, who closed which issue, when, and on what resource.
- When
- Who
- What happened
- Type
Launching soon
From answering questions to doing the work
A person no longer has to ask. A trigger starts the work, inside the same permissions and the same audit log as everything else. Automations and live dashboards are launching soon, on the Black plan.
Automations
A schedule fires, a digest ships, approved.
Exceptions are fetched, grouped, drafted into a digest, approved by a person, then posted back.
Pydantic Logfire (EU) digest
Run 418 · started 2 minutes ago · on behalf of Emily Carter
-
✓
Schedule
Every weekday at 8:00 AM
0.2s -
✓
Fetch traces
Pydantic Logfire (EU)
1.4s -
✓
Group by owner
Transform
0.1s -
✓
Draft the digest
Agent step
Ran with 4 tools, returned a structured summary
6.2s -
Approve the digest
Needs approval
Assigned to Michael Brennan
Approve Deny -
Post the digest
Pydantic Logfire (EU)
Queued
Collections and dashboards
Exception counts, computed on a schedule, no asking.
Four metrics, 14 days of records created, a split by team, refreshed with no model involved.
Pydantic Logfire (EU) health
Refreshed 4 minutes ago · every 15 minutes · from the traces collection
Traces
1,284 ↓ 12%
Exceptions
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Traces created
Last 14 days
By team
Share of activity
Production 34%
Staging 27%
On-call 21%
Platform 18%
FAQ
Frequently asked questions
How do I connect Pydantic Logfire (EU) to Claude?
Two steps. In Elaichi, pick Pydantic Logfire (EU) and connect it over OAuth: you sign in to your EU Logfire account and approve access, with no client ID or secret to generate. Then in Claude open Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Claude now reaches Pydantic Logfire in EU as you.
Does Pydantic Logfire (EU) work with ChatGPT and Cursor as well as Claude?
Yes. Pydantic Logfire (EU) is connected once in Elaichi, and the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client and the Elaichi Agent. There is nothing extra to set up per client.
What can an AI agent actually do with my Pydantic Logfire (EU) data?
It can run SQL against your Pydantic Logfire (EU) telemetry, pull up recent exceptions with their traces, and create or update dashboards, alerts and issues. In practice you ask things like which errors appeared after the last deploy or whether an alert is still firing. Short, concrete asks work better than long sentences.
Does connecting Pydantic Logfire (EU) give the AI everything in my project?
No. Every call to Pydantic Logfire in EU runs as the person who signed in, so the agent sees only the projects and telemetry that person can already see. Elaichi can narrow that further with roles and restrictions, and it can never widen it.
Can I stop an agent from deleting or changing things in Pydantic Logfire (EU)?
Yes. Restrictions in Elaichi work per action, so you can allow reading telemetry and exceptions from Pydantic Logfire (EU) while blocking changes to dashboards, alerts or issues. A restricted action is never advertised to the AI client at all, so no prompt can reach it.
What happens to a Pydantic Logfire (EU) connection when someone leaves?
Offboarding that person in Elaichi ends their access to Pydantic Logfire (EU) at once, across every client they used. A connection they shared keeps working for everyone else on the team. If you want it gone entirely, disconnecting Pydantic Logfire in EU once in Elaichi removes it from every client.
Does the Pydantic Logfire (EU) MCP connector work with Gemini, Codex, Claude Code or other MCP clients?
Yes. Pydantic Logfire (EU) 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 (EU)?
Yes. Both let Claude, ChatGPT or Cursor use Pydantic Logfire (EU). 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 (EU) call.
How is Elaichi different from Composio for Pydantic Logfire (EU)?
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 (EU): one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.
Put Pydantic Logfire (EU) in front of your team
14 days on Gold, no credit card. Connect it once and pick what each team can call.
- Works with
-
and any other MCP client, or the Elaichi Agent.
- When the trial ends
- Nothing is deleted. Connections, roles and the audit log stay where they are, so subscribing picks up exactly where you left off.