posthog_query
Run an ad-hoc HogQL (SQL) query against a PostHog project's events.
This record as markdown: /tools/io-github-malamutemayhem-unclick-mcp-server/posthog-query.md
What posthog_query does on UnClick
AI agents invoke posthog_query to trigger actions in UnClick. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
host | string | — | PostHog host (default https://us.posthog.com) |
query | string | Yes | HogQL/SQL query (e.g. select count() from events) |
api_key | string | Yes | PostHog Personal API key |
project_id | string | — | PostHog project id (can be a saved default) |
Parameters from the server's own tool schema.
Why posthog_query is rated High
This tool executes arbitrary SQL-like queries against a PostHog project. While the primary use case is reading analytics data, the ability to run ad-hoc HogQL/SQL queries means it could execute complex or destructive operations depending on what HogQL supports.
From the tool's definition "Run an ad-hoc HogQL (SQL) query against a PostHog project's events"
Risk signalsAccepts URL/endpoint input (host) · Handles credentials or secrets (api_key)
Attacks that exploit this kind of access
The rule that runs posthog_query safely
PolicyLayer is an MCP gateway: it sits between your AI agents and UnClick, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For posthog_query, this is the rule to start with:
posthog_query stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect UnClick, apply this rule, and every posthog_query call is checked against it from then on.
Questions about posthog_query
Run an ad-hoc HogQL (SQL) query against a PostHog project's events. It is categorised as a Execute tool in the UnClick MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
posthog_query accepts 4 parameters: host, query, api_key, project_id. Required: query, api_key. The full parameter table on this page comes from the server's own tool schema.
Register the UnClick MCP server in PolicyLayer and add a rule for posthog_query: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches UnClick. Nothing to install.
posthog_query is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the posthog_query rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for posthog_query. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
posthog_query is provided by the UnClick MCP server (@unclick/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on UnClick, and thousands of servers like it.
Across the catalogue