# Axiom MCP connector The Axiom connector lets Claude, ChatGPT, Cursor, or the Elaichi Agent query your logs and metrics, read dashboards, and check monitors, with each person signed in as themselves and every call recorded in an audit log. Source: https://elaichi.ai/connectors/axiom/ ## Facts | | | | --- | --- | | Application | Axiom | | Category | Observability | | AI tools | 31 | | Authentication | Connects over OAuth | | Bring your own OAuth app | No | | Native MCP | Yes. Axiom builds and runs this MCP server. Elaichi adds sign-in, access controls and an audit log on top | | Support for its tools | axiom.co/support | | 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 Axiom is connected - Which monitors fired in the last 24 hours? - Show error counts by service from the production dataset today. - Create a dashboard for checkout latency over the past week. ## Connect Axiom in Elaichi This happens once for the organization, before any client is involved. 1. Open Connections, choose Add connection, and pick Axiom. 2. Optionally set Share with, then press Connect. 3. Approve it in Axiom. Axiom'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 Axiom tools are exposed, rename them, or freeze arguments before anyone points a client at it. ## Axiom 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. ## Axiom 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. ## Axiom 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 Axiom 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 Axiom 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 Axiom through Elaichi ### Find the error behind a customer report Engineering. Ask what happened in a dataset around the time a customer reported a failure and get the matching log lines back in plain language. ### Check which monitors are firing right now On-call. Before a handover, ask for the monitors currently in alarm and their recent history so the next person starts with the full picture. ### Confirm an outage before replying to a ticket Support. Ask whether requests for a given account failed in the last hour, then reply to the customer with what actually happened. ### Build a dashboard for a new feature Product. Describe the charts you want, such as sign-ups by region or latency over the last day, and have the dashboard created in Axiom. ### Trace suspicious activity across datasets Security. Ask which datasets hold authentication logs, then query them for repeated failed logins from one address over the past week. ### Set up a monitor for a new service Platform. Ask for a monitor that fires when error rates cross a threshold and routes to the team's existing notifier. ## Elaichi vs Zapier MCP vs Composio for Axiom All three can connect Axiom 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 Axiom tools | Allow or restrict single Axiom 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 Axiom 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 Axiom to Claude? Connect Axiom in Elaichi first. Axiom connects over OAuth, so you sign in to Axiom and approve access, 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. Claude signs you in through Elaichi and can start querying Axiom. ### Does Axiom work with ChatGPT and Cursor as well as Claude? Yes. Once Axiom is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client, and the Elaichi Agent. You connect Axiom once and every client uses it. ### What can an AI agent actually do with my Axiom data? An agent connected to Axiom can list your datasets and their fields, run queries against them, reuse saved queries, and search and query metrics. It can list, read, export, build, and edit dashboards, check which monitors are firing and their history, and create or update monitors that route to your notifiers. Short concrete asks, like which monitors fired overnight, work better than long sentences. ### Does connecting Axiom give the AI access to every dataset in my organization? No. Every call to Axiom runs as the person who signed in, so the AI sees only the datasets, dashboards, and monitors that person can already see in Axiom. Elaichi can narrow that access further for a team or a role, but it can never widen it beyond what Axiom already grants. ### Can my team share one Axiom connection? Yes. One person connects Axiom and shares it with a team in Elaichi, and nobody else ever handles an Axiom credential. Each teammate still signs in to Elaichi as themselves, so the audit log names the actual person behind every query and dashboard change. ### Can I stop an agent from deleting or changing things in Axiom? Yes. Restrictions in Elaichi apply per action, so you can allow querying Axiom datasets while blocking the deletion of dashboards or monitors. A restricted action is never advertised to the AI client at all, so no prompt can reach it. ### What happens to an Axiom connection when someone leaves? Offboarding a person in Elaichi ends their access to Axiom through every client at once. A shared Axiom connection keeps working for everyone else on the team. If you disconnect Axiom in Elaichi, it is removed from Claude, ChatGPT, Cursor, and every other client in one step. ### Does the Axiom MCP connector work with Gemini, Codex, Claude Code or other MCP clients? Yes. Axiom 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 Axiom? Yes. Both let Claude, ChatGPT or Cursor use Axiom. 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 Axiom call. ### How is Elaichi different from Composio for Axiom? 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 Axiom: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call. ## All 31 Axiom tools Every tool below is callable through https://api.elaichi.ai/mcp once Axiom is connected, subject to the toolbox it is in and the restrictions on the caller. - **Query dataset** (Search). Run an APL query against an events or traces dataset. For metrics datasets, use queryMetrics instead. - **Get saved queries** (Get). List saved APL queries in your organization. - **List datasets** (List). List available Axiom datasets. - **Get dataset fields** (Get). List fields in an events or traces dataset, including field names and types. For metrics datasets, use listMetrics and listMetricTags instead. - **Create dataset** (Create). Create a new dataset in the current organization. - **List metrics** (List). List available metric names in a dataset. - **List metric tags** (List). List tags available for filtering metrics in a dataset. - **Get metric tag values** (Get). Get values for a specific metric tag in a dataset. - **Search metrics** (Search). Search for metrics that match a known tag value. - **Query metrics** (Search). Run an MPL query against an Axiom metrics dataset. - **List dashboards** (List). List dashboards in your organization. - **Get dashboard** (Get). Get details for a dashboard by UID. - **Export dashboard** (Export). Export a dashboard as JSON. - **Create dashboard** (Create). Create a dashboard from a JSON document. - **Update dashboard** (Update). Update a dashboard by UID. - **Update dashboard chart** (Update). Patch a single chart in an existing dashboard by chart ID. - **Delete dashboard** (Delete). Delete a dashboard by UID. - **Check monitors** (Action). Check monitors and their current statuses. - **Get monitor** (Get). Get a monitor’s full definition by ID, including the complete query text. - **Get monitor history** (Get). Get alert history for a specific monitor. - **List notifiers** (List). List configured notifiers. - **Create monitor** (Create). Create a new monitor. - **Update monitor** (Update). Update an existing monitor by ID. - **Delete monitor** (Delete). Delete a monitor by ID. - **Create notifier** (Create). Create a new notifier. - **Update notifier** (Update). Update an existing notifier by ID. - **Delete notifier** (Delete). Delete a notifier by ID. - **Services get map** (Get). Get the service dependency graph, including call volume, errors, and approximate latency. - **Services get changes** (Get). Report what changed in the service dependency graph, such as new or missing dependencies and latency regressions. - **Services get edge history** (Get). Get time-series history for a service’s dependency edges. - **Send feedback** (Send). Send feedback to the Axiom team about MCP tool descriptions, results, errors, or missing capabilities.