Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.oneperfectslice.ai/llms.txt

Use this file to discover all available pages before exploring further.

Set up your client

Install takes under 2 minutes. Pick your client:

Claude Code

One CLI command. Best for developers in the terminal.

Claude Desktop

Edit a JSON config. Best for non-technical users.

Codex

One CLI command. For OpenAI Codex users.

How it works

The MCP server sits on top of the OnePerfectSlice REST API and exposes 9 tools designed for agent interaction. Key differences from calling the API directly:
  • Composite operationsrun_slice starts a run, polls for up to 30 seconds, and fetches evidence on completion. One tool call, not three.
  • Flat parameters — no nested objects. Every filter is a top-level argument the agent can set directly.
  • Guided errors — when something goes wrong, error messages tell the agent exactly which tool to call next.

Available tools

ToolWhat it does
list_slicesDiscover available analyses or get details for a specific slice
preview_slice_countCount matched calls before running (free, no AI cost)
run_sliceExecute an analysis and get results + evidence
get_runRetrieve results from a past or in-progress run
list_runsBrowse run history with optional filtering
search_postsFind summaries and scorecards matching your criteria
get_postGet a single post with full structured content
search_evidenceSearch evidence quotes across all completed runs
get_filter_optionsDiscover valid filter values (call owners, companies, CRM data)
See Tools for the full parameter reference with examples.