# Observability MCP connectors for Claude, ChatGPT and Cursor 15+ Observability connectors in the Elaichi catalog, each callable through https://api.elaichi.ai/mcp once connected, under the same roles, restrictions and audit log as the rest of the catalog. Source: https://elaichi.ai/connectors/category/observability/ | | | | --- | --- | | Category | Observability | | MCP endpoint | https://api.elaichi.ai/mcp | | Works with | Claude, ChatGPT, Cursor, any MCP client, and the Elaichi Agent | ## Observability connectors - [Axiom](https://elaichi.ai/connectors/axiom/) — 31 tools · hosted sign-in - [Datadog (AP1)](https://elaichi.ai/connectors/datadog-ap1/) — 352 tools · hosted sign-in - [Datadog (AP2)](https://elaichi.ai/connectors/datadog-ap2/) — 352 tools · hosted sign-in - [Datadog (EU)](https://elaichi.ai/connectors/datadog-eu/) — 352 tools · hosted sign-in - [Datadog (UK1)](https://elaichi.ai/connectors/datadog-uk1/) — 352 tools · hosted sign-in - [Datadog (US1)](https://elaichi.ai/connectors/datadog/) — 352 tools · hosted sign-in - [Datadog (US3)](https://elaichi.ai/connectors/datadog-us3/) — 352 tools · hosted sign-in - [Datadog (US5)](https://elaichi.ai/connectors/datadog-us5/) — 352 tools · hosted sign-in - [Grafana Cloud](https://elaichi.ai/connectors/grafana/) — 62 tools · hosted sign-in - [Honeybadger](https://elaichi.ai/connectors/honeybadger/) — 39 tools · hosted sign-in - [Honeybadger (EU)](https://elaichi.ai/connectors/honeybadger-eu/) — 39 tools · hosted sign-in - [Honeycomb](https://elaichi.ai/connectors/honeycomb/) — 34 tools · hosted sign-in - [LogRocket](https://elaichi.ai/connectors/logrocket/) — 8 tools · hosted sign-in - [Monte Carlo](https://elaichi.ai/connectors/monte-carlo/) — hosted sign-in - [New Relic](https://elaichi.ai/connectors/newrelic/) — 54 tools · API key - [Pydantic Logfire](https://elaichi.ai/connectors/logfire/) — hosted sign-in - [Pydantic Logfire (EU)](https://elaichi.ai/connectors/logfire-eu/) — hosted sign-in - [Vantage](https://elaichi.ai/connectors/vantage/) — 226 tools · API key ## What teams do with Observability connectors ### Engineering - **Find the slow request after a deploy** (Datadog (AP1)) — Ask which spans got slower in the last hour and have the agent set them beside the error logs for the same service. - **Trace a slow request end to end** (Datadog (AP2)) — Fetch a trace by id, aggregate the spans by service and spot the hop that is taking the time. - **Trace a slow request to the service at fault** (Datadog (EU)) — Search traces and spans for a request, aggregate them by service, and find where the time is going without clicking through flame graphs. ### Support - **Check the logs behind a customer ticket** (Datadog (UK1)) — Search the logs and real user monitoring events for the customer's session while the ticket is still open, so the reply to them is based on what actually happened. - **Check whether a customer's problem is real** (Datadog (US1)) — When a customer reports errors, look up the RUM events and logs for their session in Datadog (US1) before replying, so the answer is grounded in what actually happened. - **Check the logs behind a customer ticket** (Datadog (US3)) — Search logs for the customer's account around the time they reported the problem, and attach what you found to the ticket. ### Platform - **Spot hosts that stopped reporting** (Datadog (US5)) — Search hosts by tag or environment and ask which ones have gone quiet since the last deploy. - **Find the dashboard nobody can locate** (Grafana Cloud) — 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. - **Check workload health before a release** (New Relic) — Ask which New Relic workloads are degraded right now and which services and hosts sit inside them, then decide whether to ship or hold. ### On-call - **Triage a noisy fault during an incident** (Honeybadger) — Pull the notices and occurrence counts for a fault, mark it resolved or assigned in Honeybadger, and leave a comment that says what was done and when. - **Understand a fault before opening the dashboard** (Honeybadger (EU)) — Pull the latest notices for a fault, see which environment and which users were affected, and leave a comment with what you found for the next person. - **Find the slow request behind a page** (Honeycomb) — Ask for the trace behind a latency alert, see which spans took the time, and get a plain summary before you open a laptop. ## Things to ask once it is connected - "Which monitors fired in the last 24 hours?" (Axiom) - "Which monitors fired for the checkout service in the last hour?" (Datadog (AP1)) - "Which monitors are alerting in production right now?" (Datadog (AP2)) - "Which monitors are firing for the checkout service right now?" (Datadog (EU)) - "Which monitors are alerting on the checkout service right now?" (Datadog (UK1)) - "Which monitors are alerting right now and on which hosts?" (Datadog (US1)) - "Which monitors are alerting in production right now?" (Datadog (US3)) - "Which monitors fired on the checkout service in the last hour?" (Datadog (US5)) ## What an agent can call in Observability 2957 tools across the category. Of these connectors, 16 use hosted sign-in with nothing to register first; 2 connect with an API key or app credentials an admin pastes once. ## Frequently asked questions ### How many Observability connectors does Elaichi have? 15+ 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, any MCP client and the Elaichi Agent all connect to that same address with OAuth. 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. 16 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 never advertised to the model, so it cannot be called or guessed at from the tool list. 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. [Browse the full connector catalog](https://elaichi.ai/connectors/)