by Axiom
Updated October 20, 2026
MCP100 verdict
Not currently recommended. First-party evidence supports Shortlist admission; this is not a Recommended-tier security certification.
MCP100 Assessment
Editorial verdict
Reviewed October 19, 2026
Task Fit
Mapped
Specialized workflows
Trust
Status warning
Shortlist evidence is sufficient for identity, setup and task value; authenticated runtime tool-schema measurement and exhaustive security certification remain out of scope.
Maintenance
Date unavailable
No dated repository or package update is currently stored.
Popularity
Signals unavailable
No independently comparable adoption metric is currently stored.
Evidence scope
16 shared-repository stars · not MCP-specific
No MCP-specific package metric is stored
Repository identity: axiomhq/skills
Stars observed October 20, 2026 · Downloads observed October 20, 2026
Current Axiom skills repository bundles the hosted Axiom MCP connection plus agent skills. The current MCP is hosted; this repository is distribution/skills evidence, while the older `axiomhq/mcp-server-axiom` implementation is archived.
Hosted Axiom MCP has no exact public package distribution verified.
Publisher activity observed October 20, 2026
Current source snapshot
Source relationship: First-party MCP
Reviewed October 19, 2026
Evidence-backed setup
Choose your MCP client. A client connects to the MCP server; the language model is selected inside that client. Only stored, source-backed configurations are shown.
Transport not recorded
Complete client-specific setup, verification and removal are not documented in this reviewed source.
Publisher-documented setup is not the same as MCP100 execution testing. “MCP100 logic checked” means the stored configuration shape was reviewed, not that third-party MCP software was run.
Evidence checked 2026-10-20
Type-appropriate, source-backed setup for this mcp server profile.
Loading optional publisher installation details…
{"url":"https://mcp.axiom.co/mcp"}Capability
Axiom MCP is a first-party MCP for investigate and manage axiom observability data, dashboards, monitors, and service maps. Authentication/setup: OAuth; personal access token + organization ID also supported. Write tools can create or change datasets, dashboards, monitors, and notifiers. Use least privilege. Do not attribute the archived legacy mcp-server-axiom repository's stars to the current hosted service.
Current official tools reference was rechecked on 2026-10-20.
Not measured yet
Estimated token footprint of the MCP tool schemas exposed to the agent.
https://mcp.axiom.co/mcp
Reviewed access
Related reviewed MCPs
Query Grafana Cloud metrics, logs, dashboards, and observability context.
Choose this instead if
Choose Grafana Cloud MCP instead if query Grafana Cloud metrics, logs, dashboards, and observability context.
Query Grafana Cloud metrics, logs, dashboards, and observability context.
Investigate Datadog logs, metrics, traces, monitors, dashboards, and security signals.
Choose this instead if
Choose Datadog MCP instead if investigate Datadog logs, metrics, traces, monitors, dashboards, and security signals.
Investigate Datadog logs, metrics, traces, monitors, dashboards, and security signals.
Search and investigate governed Splunk Cloud Platform data through granular MCP tools.
Choose this instead if
Choose MCP Server for Splunk platform instead if security and operations investigation over authorized Splunk searches and platform objects.
Search and investigate governed Splunk Cloud Platform data through granular MCP tools.
Axiom is listed as First-party MCP in MCP100’s current evidence.
Current official resources:
From the publisher README
Original client setup and configuration retained from the publisher documentation.
Publisher-documented clients
These names appear in the publisher's installation documentation. MCP100-verified configurations are shown separately above when available.
Register Axiom's marketplace so Codex can find its plugins:
codex plugin marketplace add axiomhq/skills
Install the Axiom plugin, which includes all skills in this repository and the hosted MCP server connection:
codex plugin add axiom@axiom
In axiom@axiom, the first name is the plugin and the second is the marketplace.
Authorize Axiom in your browser when prompted. If you already added Axiom MCP manually, keep one connection to avoid duplicate tools.
To update, run codex plugin marketplace upgrade axiom, then codex plugin add axiom@axiom. Start a new session to use the update.
claude plugin marketplace add axiomhq/skills
claude plugin install axiom@axiom
Restart Claude Code, then use /mcp to authorize Axiom.
To update, run claude plugin marketplace update axiom, then claude plugin update axiom@axiom. Restart Claude Code to load it.
On Teams or Enterprise, an admin must enable Allow Local Plugin Imports. Then clone into Cursor's local plugin directory:
git clone https://github.com/axiomhq/skills.git ~/.cursor/plugins/local/axiom
Reload Cursor and authorize Axiom when prompted. To update an existing install, run git -C ~/.cursor/plugins/local/axiom pull --ff-only, then reload Cursor.
Teams and Enterprise admins can also import axiomhq/skills through Plugins & MCPs → Add Marketplace → Import from Repo in the Cursor dashboard. See Cursor's plugin guide.
gemini extensions install https://github.com/axiomhq/skills
Restart Gemini CLI, then use /mcp auth axiom to authorize Axiom.
To update, run gemini extensions update axiom, then restart Gemini CLI. See the Gemini extension reference.
npx skills add axiomhq/skills
This installs all skills. Skills have dependencies on each other (e.g., axiom-controlling-costs depends on axiom-sre and axiom-building-dashboards), so installing all is recommended.
For SRE, run scripts/init from the installed skill directory; its location depends on your agent or plugin installer. From a checkout of this repository:
./skills/sre/scripts/init
This initializes SRE configuration and memory under ~/.config/axiom-sre/. Edit the generated config.toml to add your deployments, then run the initializer again. See SRE setup for configuration and migration from ~/.axiom.toml.
Original product, capability, tool, and usage documentation from the MCP publisher. Installation sections appear under Install & Agents.
Agent skills for working with Axiom. Skills are folders of instructions, scripts, and resources that coding agents load dynamically to improve performance on specialized tasks.
| Skill | Description |
|---|---|
| axiom-sre | Hypothesis-driven SRE investigation with Axiom |
| axiom-spl-to-apl | Translate Splunk SPL queries to Axiom APL |
| axiom-building-dashboards | Design and build Axiom dashboards from intent, templates, Splunk migrations, and metrics/MPL chart payloads |
| axiom-alerting | Unified monitor + notifier management for Axiom alerting via the v2 API |
| axiom-controlling-costs | Analyze query patterns to find unused data and optimize Axiom costs |
| axiom-metrics-chart | Render saved metrics v2/v3 JSON as line charts; zero-dependency ASCII by default, optional gnuplot PNG/SVG/sixel |
brew install jq or apt install jq)brew install bc or apt install bc)brew install coreutils on macOS).mcp.json configures the hosted Axiom MCP Server at https://mcp.axiom.co/mcp for agent clients that install plugins from a manifest. APL queries use queryDataset; metrics queries use queryMetrics with MPL. See the MCP setup docs.
Skills use your configured credentials to query Axiom and optional Grafana, Pyroscope, Sentry, Slack, and Kubernetes connections. They can update dashboards and alerts. SRE stores investigation memory locally and can sync it to a Git repository you configure.
SRE uses ~/.config/axiom-sre/config.toml with [axiom.deployments.<name>] sections. Dashboard, alerting, and metrics scripts use the separate ~/.axiom.toml format below. Cost-control workflows use SRE for queries and dashboard scripts for deployment, so configure both when using those workflows. MCP OAuth does not configure these script credentials.
For scripts that use ~/.axiom.toml, add your deployment(s):
[deployments.prod]
url = "https://api.axiom.co"
token = "xaat-your-api-token"
org_id = "your-org-id"
[deployments.staging]
url = "https://api.axiom.co"
token = "xaat-your-staging-token"
org_id = "your-staging-org-id"
To get these values:
org_id - The organization ID. Get it from Settings → Organization.token - Use an advanced API token with minimal privileges.The deployment name (e.g., prod, staging) is passed to scripts: scripts/axiom-query prod "..."
Use conventional commit titles: feat:, fix:, or docs:. Release Please opens a PR to update version.txt, all five client manifests, and CHANGELOG.md. The daily run also picks up SRE sync commits.
SRE syncs and eval baseline updates also open PRs. On bot PRs, click Approve workflows to run if GitHub requests it, then review and merge once CI passes. SRE changes still come from Gilfoyle; update their source there.
Merging the release PR automatically creates a GitHub release and attaches axiom-openai-plugin.zip from that commit. Download the ZIP and submit it to OpenAI using the docs below.
MIT License - see LICENSE