Statsig
Use the Statsig MCP to inspect and manage Statsig entities such as gates, experiments, dynamic configs, segments, metrics, audit logs, and results.
Install
$ agentstack add skill-statsig-io-agent-skills-statsig ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-statsig-io-agent-skills-statsig) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Statsig MCP
Overview
Use the Statsig MCP server to inspect and manage Statsig entities, review rollout state, check experiment or gate results, inspect audit history, and answer configuration questions.
Setup Statsig MCP
Important: you must check to see if the Statsig MCP server is running. If not, tell the user how to configure Statsig:
Add this to ~/.codex/config.toml and replace the API key:
[mcp_servers.statsig]
command = "npx"
args = ["--yes", "mcp-remote", "https://api.statsig.com/v1/mcp", "--header", "statsig-api-key: console-YOUR-CONSOLE-API-KEY"]
trust_level = "trusted"Use a Statsig Console API key with the permissions you need (read-only for viewing, write for changes). Statsig API keys can be created under Settings -> Keys & Environments. Restart Codex after editing the config.
Workflow
- Analyze the user's query and determine the task type: discovery, inspection, results analysis, audit/history review, or config changes.
- Identify the relevant Statsig entity types and names when possible. Common entities include gates, experiments, dynamic configs, segments, metrics, metric sources, and param stores.
- Use list or search-style MCP tools first when the user does not provide an exact identifier. Use detail tools once you know the target object.
- For performance or rollout questions, use the appropriate results endpoints or audit logs to understand behavior over time.
- For create or update requests, confirm the intended object, preserve required fields, and apply the matching write tool carefully.
- Summarize the key findings or changes clearly, including the object name, current state, important rules or metrics, and any follow-up actions.
MCP usage
Use the MCP to fetch, inspect, create, and update Statsig objects. For the current capability list and example prompts, read references/statsig-mcp.md.
Resources
references/statsig-mcp.md: setup notes, MCP capabilities, and example prompts for Statsig MCP.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: statsig-io
- Source: statsig-io/agent-skills
- License: ISC
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.