NewAgent Observability is live.
The vendor directory

AI observability tools: what your agent can actually query

This directory covers 90 monitoring and developer tools. For each one we looked for an MCP server, the connector that lets an AI coding agent query the tool directly, and put it through the same four checks: is it official, maintained, published somewhere you can install it from, and usable. Every fact comes from the vendor's own documentation, public repositories and package registries, with the date it was checked.

Browse by the part of the work you are in

1Code, tests & reviewAgents writing code, generating tests and reviewing pull requests as one loop.2CI & releasePipelines running far more often, and releases compressing from weeks to hours.3Production observabilityInfrastructure, APM, logs, traces, profiling and incident response, with an agent as the reader.4Agent observability & evalsWatching the agents themselves: hallucination, drift, eval scores and what a session actually did.5AI cost managementToken cost, model routing and spend governance.
Filter by:

Official server means the vendor publishes and maintains it. Official, abandoned means the vendor published one and no longer maintains it. Community only means someone outside the vendor built it. MCP client, not a server means the tool uses servers published by other tools and offers none of its own. No server found means neither the vendor nor the community publishes one that exposes the tool's data.

Allure TestOps logo

Allure TestOps

Official server13 tools built into TestOps from 26.1.1. A public beta that may later carry a fee.Code & reviewRead the guideArize Phoenix logo

Arize Phoenix

Official server27 tools reaching traces and spans, not just evaluations. Works against self-hosted Phoenix too.Code & reviewAgent obs & evalsRead the guideAviator logo

Aviator

Official server3 runbook tools. Aviator's own docs call this the legacy path and prefer its CLI.CI & releaseRead the guideAWS Cost Explorer logo

AWS Cost Explorer

Official server38 tools over billing, budgets and optimization. The fifth-heaviest connector here at about 26,390 tokens.AI costRead the guideAzure Cost Management logo

Azure Cost Management

Official serverMicrosoft's ARM server reads real Azure spend. 14 cost tools, 5 on by default, GitHub Copilot clients.AI costRead the guideBigPanda logo

BigPanda

Official serverOne tool per enabled Biggy action plan. Every tool takes a natural-language query.ProductionRead the guideBraintrust logo

Braintrust

Official server34 documented tools across 9 categories, led by SQL over your own logs.Code & reviewAgent obs & evalsRead the guideBuildPulse logo

BuildPulse

Official server5 tools for flaky-test triage, about 686 tokens. Among the cheapest connections measured here.Code & reviewRead the guideCircleCI logo

CircleCI

Official server13 tools for pipelines, builds and flaky tests. The npm package is deprecated; use the hosted server.CI & releaseRead the guideClaude Code logo

Claude Code

Official serverMostly an MCP client. `claude mcp serve` exposes its own tools over stdio.Code & reviewRead the guideCline logo

Cline

Official serverIts only server files GitHub issues about Cline. No Cline data is exposed.Code & reviewRead the guideCloudZero logo

CloudZero

Official server15 cost tools with a published 3,000-call daily quota. OAuth use is unmetered.AI costRead the guide

Showing 12 of 90

The pattern across all 90 vendors

An MCP server can only return what its backend kept

Connectors cap results and sample telemetry, usually without saying so. An agent can then report that nothing was found when the records exist. Oodle's own MCP server reads telemetry that was never sampled or rolled up, so the agent sees all of it.

See agent observability