Skip to content

Connectors / Observability

Observability MCP connectors for Claude, ChatGPT and Cursor

10+ Observability connectors in the catalog, each behind the same governed MCP endpoint as everything else in Elaichi.

Start 14-day free trial Browse the full catalog
https://api.elaichi.ai/mcp The same for every user.

  • Their own access. An agent never gets more than the person it acts for.

  • One connection, every client. Claude, ChatGPT, Cursor, any MCP client, and the Elaichi Agent.

The connectors

Observability connectors in the catalog

Connect one and your whole team reaches it, each inside the access they already have, without anyone handling a credential.

10 connectors

Browse all 600+ connectors →

In practice

What teams do with Observability connectors

Drawn from the connector pages in this category, so every line describes something one of these connectors actually does.

Engineering

  • Datadog

    Trace a slow request to its cause

    Find the spans behind a slow endpoint, compare them with the metric for that service and see where the time goes.

  • Grafana Cloud

    Catch a dashboard up after a deploy

    Read the queries behind each panel, then update the dashboard when a metric name or label changed in the release, instead of editing panels one at a time.

  • New Relic

    Map every entity in a workload

    List the services, hosts, and other entities grouped under a New Relic workload, along with their tags, to see what a team actually owns.

Support

  • Honeybadger

    Check whether a customer hit a known fault

    When a ticket comes in, ask whether that user appears among the affected users on any open Honeybadger fault, and get the fault's status and the last comment on it.

  • Honeycomb

    Confirm a customer's reported error

    Ask for recent spans from that customer's requests and get a plain answer you can paste into the ticket.

  • Axiom

    Confirm an outage before replying to a ticket

    Ask whether requests for a given account failed in the last hour, then reply to the customer with what actually happened.

Platform

  • Pydantic Logfire

    Build a dashboard from a plain question

    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.

  • Datadog

    Review monitors before they go live

    Validate a new monitor against Datadog, compare it with the monitor templates your team already uses and check which monitor group it belongs in.

  • Grafana Cloud

    Find the dashboard nobody can locate

    Search dashboards and folders by name or keyword, get a summary of what each one shows, and send a deep link to the person who asked.

Product

  • LogRocket

    Check whether a new issue is spreading

    Ask which issues in the web app project appeared this week and how many sessions each one touched, then decide what goes into the next sprint.

  • Grafana Cloud

    Get a weekly usage number in plain words

    Ask for the metric behind sign-ups or orders over the past seven days and get a figure from Prometheus, without learning a query language first.

  • Honeybadger

    See which release broke things

    Query Honeybadger insights for error trends across projects after a deploy, and compare this week's occurrence counts against the week before.

Once it is connected

Things to ask

Each of these is answered against the access the person asking already has, in the Observability account you connected.

  • Which monitors fired in the last 24 hours?

    Axiom

  • Which monitors are alerting right now and on which hosts?

    Datadog

  • Show the Prometheus error rate for checkout over the last hour

    Grafana Cloud

  • Which faults in the production project spiked in the last 24 hours?

    Honeybadger

  • Which spans made checkout slow in the last hour?

    Honeycomb

  • Find sessions from acme.com this week that hit a checkout error

    LogRocket

  • Which alerts fired on the orders table overnight?

    Monte Carlo

  • List New Relic users added to the SRE group this month

    New Relic

The tools

What an agent can call in Observability

Connectors
10+

in the Observability catalog

Tools
806

callable the moment you connect

Hosted sign-in
8

connect with nothing to register

Of those 806 tools, 8% delete something. Restricting an agent to reads is not a promise here, it is 434 tools admitted and the rest left out — and a restricted tool is never advertised to the model at all.

Read 54%
434 tools · list, get, search
Write 22%
178 tools · create, update, send
Delete 8%
61 tools · delete, remove, archive
Other 17%
133 tools · vendor-specific verbs

One endpoint

https://api.elaichi.ai/mcp

Every connector above answers here.

Every Observability connector, by depth

Tool counts are what the connector exposes today; the split is what those tools do.

Hosted sign-in takes a partnership with each vendor, and more are in progress. Until one lands, Your own app means the connector works today — you register an OAuth app once and connect. API key and App credentials mean an admin pastes them once, with nothing to register.

Observability connectors with tool counts split by read, write and delete
Connector Tools Read · write · delete Sign-in
Datadog 352 Hosted
Vantage 226 API key
Grafana Cloud 62 Hosted
New Relic 54 API key
Honeybadger 39 Hosted
Honeycomb 34 Hosted
Axiom 31 Hosted
LogRocket 8 Hosted
Monte Carlo Hosted
Pydantic Logfire Hosted

FAQ

Frequently asked questions

How many Observability connectors does Elaichi have?

10+ Observability connectors are in the catalog today, and the list grows as connectors are added. Each one arrives as a set of MCP tools an agent can call through https://api.elaichi.ai/mcp.

Can Claude, ChatGPT and Cursor all use Observability connectors?

Yes. Elaichi exposes one organization-wide endpoint, https://api.elaichi.ai/mcp, and Claude, ChatGPT, Cursor or any MCP client connects to that same address with OAuth, while the Elaichi Agent reaches the same tools inside the app. Connecting a Observability account once makes it reachable from every one of them.

Do Observability connectors work with Gemini, Codex, Claude Code or other MCP clients?

Yes. Observability connectors are reached over the same MCP endpoint every client uses, so anything that speaks MCP can call them — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor and the Elaichi Agent. There is no per-client setup beyond pointing the client at https://api.elaichi.ai/mcp.

Do Observability connectors need me to bring my own OAuth app?

No. 8 of the Observability connectors use Elaichi's hosted sign-in, with nothing to register. 2 connect with an API key or app credentials that an admin pastes once, with no app to register. Nothing in this category asks you to register an OAuth app before you start.

Can I stop an agent from writing to Observability tools?

Yes. Tool restrictions apply at role and individual level, and a restricted tool is left out of the model's tool list and cannot be called. Read-only access to a Observability connector is a matter of allowing the reads and leaving the writes out.

Whose access does an agent get on a shared Observability connection?

The access of the person the agent is acting for, resolved against their current role on every call — not the access of whoever connected the account. A colleague can use a connection without ever seeing its credential.

Put Observability connectors in front of your team

14 days on Gold, no credit card. Connect one and pick what each team can call.

Start free trial Talk to us
Works with
Claude ChatGPT Cursor 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.