{"id":"ai.ptally/ptally","slug":"ai-ptally-ptally","title":"Ptally","description":"Insurance pricing: build, validate and test rating models, then price quotes from your AI client.","version":"1.0.0","publisher":{"kind":"domain","id":"ptally.ai","label":"ptally.ai","url":"https://ptally.ai"},"website":"https://ptally.ai/developer/mcp","repository":"","remotes":[{"type":"streamable-http","url":"https://app.ptally.ai/mcp"}],"packages":[],"published":"2026-11-04","updated":"2026-11-04","status":"online","auth":"","latency_ms":1371,"checked":"2026-11-19","uptime":100,"checks":3,"tools":[{"name":"get_docs","title":"Guides","description":"Fetch Ptally documentation by topic. Call BEFORE building or editing a config to load the rules and reference material you need. Topics: \"rules\" = agent rules, constraints, expression syntax, quality gates, and debugging guidance (start here); \"readme\" = full engine reference with step types, query language, input/output blocks, and code examples.","read_only":true},{"name":"get_schema","title":"Model layout","description":"Fetch the full JSON schema for Ptally project config files. Use to check exact field requirements, allowed step types, and property constraints.","read_only":true},{"name":"validate_project","title":"Check a model for mistakes","description":"Server-side schema validation of a project config. Returns { valid: true/false, errors: [...] } with the JSON path, keyword, and message for each issue. Prefer local validation against get_schema during authoring; use this as a ground-truth check, including on an amended model before handing it back to the user as a file. Pass exactly one of inline `project` or a base64-gzipped `project_gz` (if th","read_only":true},{"name":"get_starter","title":"Example models","description":"Fetch a worked-example Ptally project for a common line of business. Each example is a small, fully valid project with realistic collection tables, calculations, exclusions and refers, plus an embedded tests[] suite for reference. Use as a template — copy and adapt rather than authoring from scratch. Pass no arguments (or `list: true`) to get the catalog.","read_only":true},{"name":"get_projects","title":"List projects","description":"List every project stored on this self-host instance. Returns `{ count, projects: [{ project_reference, name, description }] }`. Descriptions are truncated to 100 characters so the response stays compact — call get_project for the full record. Archived projects are excluded.","read_only":true},{"name":"get_project","title":"See a project","description":"Fetch a project by `project_reference` from the self-host store. Optional `version_reference` pins to a specific version of that project (a version from another project is a tool error); otherwise the latest live (published or approved) version is used, or the latest non-archived version of any status if none is live. Returns `{ project_reference, version_reference, version, name, description, sta","read_only":true},{"name":"get_quotes","title":"List quotes","description":"List quotes stored on this self-host instance, newest first (`direction: \"asc\"` for oldest first). Filter by `project_reference` (from get_projects), `version_reference`, `journey_reference` (exact; the caller's own case id, shared by every quote in one journey, so `direction: \"asc\"` shows how that case changed over time), `since` (ISO date) or `search` (text match on indicator, quote_reference or","read_only":true},{"name":"get_journeys","title":"List journeys","description":"List journeys stored on this self-host instance. A journey is a collection of quote snapshots that build up to a complete sold (bound) journey: every quote saved with the same `journey_reference` (any string unique to the journey, e.g. an application or state-machine id) is a snapshot of the case at that point. The journey is complete when its latest quote is `sold`; until then it is in progress. ","read_only":true},{"name":"get_journey","title":"Read a journey","description":"Every quote snapshot in one journey, oldest first, in the get_quotes shape. A journey is a collection of quote snapshots, all saved with one `journey_reference`, that build up to a complete sold (bound) journey; it is complete when its latest quote is `sold`. Returns `{ journey_reference, start_date, end_date, quote_count, limit, offset, has_more, quotes: [{ quote_reference, project_reference, pro","read_only":true},{"name":"get_quote","title":"Review a quote","description":"Review one quote in a standard shape, from a stored `quote_reference` (get_quotes) or a pasted `quote` — the dashboard's Copy JSON, a POST /quotes or run_quote response, or a bare engine output with `debug` (`quote_gz`: base64 gzip of the same JSON, for big pastes). Pass exactly one. Returns `{ source, quote_reference, project_reference, project_name, version_reference, version, created_at, quoted","read_only":true},{"name":"amend_quote","title":"Amend a quote","description":"Amend a SAVED quote (a quote_reference from get_quotes): its `result`, and optionally `valid` or `sold`, with a required `reason`. Logged in the quote's audit trail under the signed-in user, with the time, the old and new values, source \"mcp\" and the reason. The engine's own result, valid and output are never changed — the amended values sit beside them, and setting the result or validity back to ","read_only":false},{"name":"run_quote","title":"Try a quote","description":"Run a quote against a stored project: a dry run by default, saved only with `save: true`. Takes `project_reference`, an optional `version_reference` (defaults to the latest live version; there is no fallback to drafts, so pass `version_reference` to run one — it must belong to the project and not be archived, else a tool error), and an `input` payload that matches the project's input schema. Runs ","read_only":false},{"name":"run_version_tests","title":"Run a version's tests","description":"Run every test in a version's tests[] against that version's stored model and compare each with its expected output. Takes `version_reference` (any status but archived — a draft after patch_version, or a live version for a baseline). Runs against the stored model, so a patch saved a moment ago is included. A test passes when its result is within 0.005 of the expected result and its valid flag equa","read_only":true},{"name":"patch_version","title":"Edit a draft","description":"Change a DRAFT version's stored model with an RFC 6902 JSON Patch, merged on the server. Use it for targeted edits; any change to a clipped collection (__context.patchable: false) goes through download and upload instead (see next_steps in get_project).\n\nBEFORE CALLING\n1. The version must be a draft: use get_project's latest_draft. If it is null, ask the user to click New Version on the project pa","read_only":false},{"name":"list_docs","title":"List project documents","description":"List the documents uploaded to a project (policy wordings, product guides, underwriting guidelines or anything else), newest first, with their indexing status. Takes `project_reference` and optional `version_reference` (only documents that apply to that version: those for every version plus any pinned to it; without it, every document on the project). Returns `{ project_reference, version_referenc","read_only":true},{"name":"search_docs","title":"Search project documents","description":"Search the documents uploaded to a project (policy wordings, product guides, underwriting guidelines or anything else) for the passages that answer a question about the product: what is covered or excluded, excesses, conditions, definitions, claims notice, eligibility. Takes `project_reference`, `query` (the question in plain words, or an exact term like \"Section 4\" or a defined term), optional `v","read_only":true},{"name":"get_doc","title":"Read a project document","description":"Read consecutive passages of an indexed document: the passage numbered `chunk` (a search_docs result's chunk) plus `before` and `after` passages either side (default 1 each, max 10). Use it when a search hit is cut off mid-clause, refers to another clause, or uses a defined term you need to read. Returns `{ document: { document_reference, title, filename, pages, chunk_count, status, … }, from, to,","read_only":true},{"name":"get_health","title":"Health check","description":"Diagnostic snapshot of the deployed MCP server plus a live probe of its store (sqlite or Postgres). Returns server name and version, protocol version, root, boot time, advertised tool names and count, a hash of the tool surface, and `store` — `{ ok, latency_ms, counts: { projects, quotes } }` from counting rows in the projects table (one row per version) and the quotes table, or `{ ok: false, late","read_only":true}],"server_info":{"name":"ptally-self-host-mcp","version":"1.0.0","tools_hash":"3a652dc62f7a8477","booted_at":"2026-11-19T18:18:02.679Z","root":"https://app.ptally.ai"},"category":"productivity","tags":["project","health","web-search"],"kind":"remote","source":"registry","submitted":{},"first_party":true,"domain_rank":null,"score":100,"indexable":true,"first_seen":"2026-11-04","stars":0,"badges":["new"],"sponsor":null,"page":"https://agentsindex.org/agents/ai-ptally-ptally/"}