Skip to content

Ptally MCP server

ai.ptally/ptallyptally.aistreamable-httpv1.0.0Scanned

Insurance pricing: build, validate and test rating models, then price quotes from your AI client.

18 tools: 4 change things and 14 only read.

Tools: 0 delete, 0 irreversible, 4 write, 14 read.
  • Reads private data · 5
  • Reads text others write · 1
  • Can send data out · 0
  • 3 findings

Tools listed without sign-in. Remote posture

With Anlyon

4 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the Ptally MCP server can do

The Ptally MCP server is published by ptally.ai, a domain the MCP Registry verified. It has 18 tools. It can create or change data (4 tools: amend_quote, run_quote, run_version_tests and patch_version), but cannot delete data. 14 tools only read.

5 tools read private data (get_docs, get_schema, list_docs and 2 more); 1 tool brings in text other people can write (get_quote).

The fixed checks matched 3 findings (long-description and annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 18, 2026, version 1.0.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

18 tools

Changes things 4Claude Code: ask
  • amend_quoteAmend a SAVED quote (a quote_reference from get_quotes): its price (`result`), and optionally `valid` or `sold`, with a required `reason`.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Amend a SAVED quote (a quote_reference from get_quotes): its price (`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 price or validity back to the engine's value clears that amendment (still logged). BEFORE CALLING 1. Call get_quote (or get_quotes) for the quote's current price, validity and sold flag. 2. Tell the user exactly what will change (old → new) and the reason that will be logged, and get their go-ahead. RULES - At least one of result, valid, sold, and each must differ from what the quote is now (else an error says nothing changed). - result is a number; valid and sold are booleans; reason is a non-empty sentence. - A sold quote is locked. The only change it accepts is `sold: false` on its own (marking it unsold, with a reason); after that it can be amended and marked sold again — three calls, each logged. Check get_quote first, and tell the user when a change means unselling the quote. A price change can go in the same call that marks it sold. - Refused in read-only mode. RESULT { quote_reference, engine: { result, valid }, now: { result, valid, sold }, amended, logged: { amendment_reference, by, at, source, result: { from, to }, valid, sold, reason }, quote_url, next_steps }.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • patch_versionChange a DRAFT version's stored model with an RFC 6902 JSON Patch, merged on the server.1 finding

    Why it is in this group

    • The name "patch_version" says "patch": a word for a change.

    Findings

    • Info

      The description is 3,762 characters long, over the 2,000 this check looks for.

      Matched text

      description ends: "...returned updated_at. Never approves or publishes — the user does that in the UI."

      What this check looks for
    Description, as the server wrote it
    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). BEFORE CALLING 1. 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 page (it copies the live model), then call get_project again. 2. Call get_project with the draft's version_reference and build every path from that response. Pass its updated_at as base_updated_at. 3. Tell the user what you will change (old → new) and get their go-ahead. PATHS (JSON Pointer) - Name steps, tests and other id'd array elements by id (else key) instead of index: /steps/<step id>/... and /tests/<test id>/... Ids survive other steps being inserted or removed in the same patch. - Model layout: /meta/..., /input/format/<input key>/... (format is an object keyed by input key), /steps/<id>/..., /output/format/<key>/..., /tests/<id>/... - Collection rows by index. Compressed collection ([[col1, col2, ...], [v1, v2, ...], ...]): index 0 is the header row, so the first data row is /collection/1, and a cell is /collection/<row>/<column index>. Uncompressed collection (array of row objects): the first row is /collection/0, and a cell is /collection/<row>/<column name>. Check __context.shape and __context.columns. - Append with "-" (/steps/-, /steps/<id>/collection/-). Insert at a numeric index; step order is execution order, so a new step goes after the steps whose outputs it reads. - Escape "~" as ~0 and "/" as ~1 inside a segment. EXAMPLES - Change a rate cell: {"op":"replace","path":"/steps/region_rates/collection/1/1","value":4.5} - Guard then change: [{"op":"test","path":"/steps/base_premium/formula","value":"<current formula>"},{"op":"replace","path":"/steps/base_premium/formula","value":"<new formula>"}] - Add a table row: {"op":"add","path":"/steps/type_factors/collection/-","value":["gravel",1.1]} - Change an input default: {"op":"replace","path":"/input/format/bike_value/def","value":2000} - Insert a step as the 5th: {"op":"add","path":"/steps/4","value":{ ...full step object... }} - Update a test's expected price: {"op":"replace","path":"/tests/t01/output/result","value":46.1} - Add a test: {"op":"add","path":"/tests/-","value":{"id":"young_rider","name":"Young rider","key":"young_rider","input":{ ...every input key... },"output":{"result":52.5,"valid":true}}}. Expectations go in output { result, valid }, even if older tests on the model keep them under result. RULES - Smallest change: replace a field, not a whole step; never the whole model (path "" is refused). - New or replaced steps follow the config constraints in the server instructions (retain: true on transforms, unique id = key, {{}} references, ...). - Don't send __context (it's stripped anyway). A clipped collection must stay exactly as stored — no edits, no removal, no replacement with the sample you saw. A patched collection may hold at most 100 rows. - All operations apply or none do. At most 200 per call. RESULT { saved, updated_at, validation, tests: { total, passed, failed, unchecked, failures: [{ test, problems }] }, version_url, next_steps }. saved: false = schema validation failed, nothing stored — fix from validation.errors and retry. A conflict error = the draft changed since you read it — call get_project again and rebuild. Tests are priced after saving and don't block it: report failures and ask whether their expected outputs should change. For every test's actual vs expected values, call run_version_tests. For another patch, use the returned updated_at. Never approves or publishes — the user does that in the UI.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • run_quotePrice a quote against a stored project: a dry run by default, saved only with `save: true`.No findings

    Why it is in this group

    • The name "run_quote" says "run": a word for a change.
    Description, as the server wrote it
    Price 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 price 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 the pricing engine and returns the quote envelope — `output`, `result`, `valid`, `status`, `error`, the engine's `errors` log, `exec_time_ms`, `dry_run: true`, a null `quote_reference`, and `documents` (the indexed project documents for the version that priced it, `[{ document_reference, title, pages }]`, to answer questions about cover with search_docs) — WITHOUT persisting a quotes row. With `save: true` the quote is stored like a POST /quotes, under the signed-in user (an engine error is stored as an error quote), and the envelope carries `dry_run: false`, its `quote_reference`, `created_at` and `quote_url`; it then shows in get_quotes and the dashboard and can be amended with amend_quote. Only save when the user asks for the quote to be kept, not to try inputs. Saving is refused in read-only mode. Call get_project first to inspect `input.format` and build a valid input.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • run_version_testsPrice every test in a version's tests[] against that version's stored model and compare each with its expected output.1 finding

    Why it is in this group

    • The name "run_version_tests" says "run": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "run_version_tests" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"idempotentHint":true,"openWorldHint":false}; The name "run_version_tests" says "run": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Price 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 equals the expected valid. Expectations are read from output { result, valid }, or, when output has neither (tests imported from the hosted service), from result { result, valid }; `expected_from` says which. A test with neither is priced but unchecked (passed: null). Returns `{ project_reference, version_reference, version, status, updated_at, total, passed, failed, unchecked, results: [{ id, name, passed, expected: { result, valid }, expected_from, actual: { result, valid }, problems, errors }], version_url, next_steps }` — `problems` says why a test failed, `errors` is up to 5 of the engine's step errors for that run. Nothing is persisted. Use after patch_version, after adding or changing tests, or before a change to record the baseline. To change a test's expected output, patch_version on /tests/<test id>/output/result (drafts only) — output takes precedence over result.

    Annotations the server declares

    • readOnlyHint: true
    • idempotentHint: true
    • openWorldHint: false
Only reads 14Show 14 read-only tools
  • get_docRead 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…Reads private dataNo findings

    Why it is in this group

    • The name "get_doc" says "get": a word for reading.

    What it can reach

    • private-dataThe name "get_doc" says "get" and "doc": it reads documents.
    • private-dataThe description's first sentence says "read" and "document": it reads documents.
    Description, as the server wrote it
    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, chunks: [{ chunk, page, section, text }] }`. chunk 0 with a larger `after` reads a document from the start. A document that isn't indexed yet is a tool error. Nothing is changed.

    Annotations the server declares

    • readOnlyHint: true
    • idempotentHint: true
    • openWorldHint: false
  • get_docsFetch Ptally documentation by topic.Reads private dataNo findings

    Why it is in this group

    • The name "get_docs" says "get": a word for reading.

    What it can reach

    • private-dataThe name "get_docs" says "get" and "doc": it reads documents.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • idempotentHint: true
    • openWorldHint: false
  • get_healthDiagnostic snapshot of the deployed MCP server plus a live probe of its store (sqlite or Postgres).No findings

    Why it is in this group

    • The name "get_health" says "get": a word for reading.
    Description, as the server wrote it
    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, latency_ms, error }`.

    Annotations the server declares

    • readOnlyHint: true
    • idempotentHint: true
    • openWorldHint: false
  • get_journeyEvery quote saved with one `client_ref`, oldest first, in the get_quotes shape: the journey from its first quote to its latest.No findings

    Why it is in this group

    • The name "get_journey" says "get": a word for reading.
    Description, as the server wrote it
    Every quote saved with one `client_ref`, oldest first, in the get_quotes shape: the journey from its first quote to its latest. Returns `{ client_ref, start_date, end_date, quote_count, limit, offset, has_more, quotes: [{ quote_reference, project_reference, project_name, version_reference, version, created_at, status, valid, result, indicator, client_ref, exec_time_ms, error, amended_result, amended_valid, sold, quote_url }], journey_url, next_steps }`. The last quote is where the case stands now; compare `result` and `valid` from one quote to the next to explain what changed, and call get_quote with a quote_reference for one quote's full review (inputs, rules that fired, how the price was built). Paged with `limit` (default and max 100) and `offset`. A client_ref with no quotes is a tool error.

    Annotations the server declares

    • readOnlyHint: true
    • idempotentHint: true
    • openWorldHint: false
  • get_journeysList client journeys stored on this self-host instance.No findings

    Why it is in this group

    • The name "get_journeys" says "get": a word for reading.
    Description, as the server wrote it
    List client journeys stored on this self-host instance. A journey is every quote saved with the same `client_ref` (the caller's own case id, e.g. a state-machine or application id); each quote is a snapshot of the case at that point. One row per client_ref, most recently active first. Each row is the journey's latest quote in the get_quotes shape (`result`, `valid`, `amended_result`, `amended_valid`, `sold`, …) plus `start_date` and `end_date` (its first and last quote's created_at), `quote_count`, `quotes` (`[{ quote_reference, created_at }]`, oldest first) and `journey_url` (the dashboard's view of it). Quotes saved without a client_ref belong to no journey. Filter by `project_reference` (only that project's quotes count), `since` (ISO date; journeys with a quote since then) or `search` (text match on client_ref). Paged with `limit` (default 25, max 100) and `offset`; `has_more` says whether another page exists. Returns `{ count, limit, offset, has_more, journeys: [...], next_steps }`. Call get_journey for one journey's quotes in full.

    Annotations the server declares

    • readOnlyHint: true
    • idempotentHint: true
    • openWorldHint: false
  • get_projectFetch a project by `project_reference` from the self-host store.No findings

    Why it is in this group

    • The name "get_project" says "get": a word for reading.
    Description, as the server wrote it
    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, status, summary, created_at, updated_at, project_url, version_url, latest_draft, clipped_collections, documents, next_steps, model }`. `documents` lists the indexed project documents that apply to this version (`[{ document_reference, title, pages }]`) — search them with search_docs. The model is a summary for reading, never a file to hand back. Every `collection` step is stamped with `__context` (`total_rows`, `shown_rows`, `columns`, `shape`, `truncated`, `patchable`; an empty table gets `total_rows: 0`, `columns: []`, `patchable: true`): tables of up to 100 rows are shown whole and can be changed with patch_version; bigger ones are clipped, listed in `clipped_collections`, and can only change by the user downloading the model from `version_url`, you amending it, and the user uploading it. `latest_draft` is the newest draft version (null if none) — patches go there, so call get_project again with its version_reference before patching. Follow `next_steps` and tell the user which route applies before making changes. All other model content — input.format, steps, expressions, output — is returned verbatim so an LLM caller can understand what the project does and how to build a valid input payload. Precursor to run_quote and patch_version.

    Annotations the server declares

    • readOnlyHint: true
    • idempotentHint: true
    • openWorldHint: false
  • get_projectsList every project stored on this self-host instance.No findings

    Why it is in this group

    • The name "get_projects" says "get": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • idempotentHint: true
    • openWorldHint: false
  • get_quoteReview 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 …Reads text others write1 finding

    Why it is in this group

    • The name "get_quote" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.

    Findings

    • Info

      The description is 2,059 characters long, over the 2,000 this check looks for.

      Matched text

      description ends: "...the part they want explained. Explain the result back following `how_to_explain`."

      What this check looks for
    Description, as the server wrote it
    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, outcome: { decision (quoted | declined | referred | error), result, valid, status, error, exec_time_ms, engine_time_ms, steps, slowest_steps }, input, output, rules: { exclusions, refers, excesses, endorsements: { fired_count, checked_count, fired: [{ step, name, exp, values, result }] } }, result_build: { formula, values, result }, valid_rule: { exp, values, result }, build: [{ order, id, name, type, description, ms, logic: [{ name, exp | formula, values, result }], lookups, table_rows, output, errors }], errors, has_trace, truncated, amendment, quote_url, version_url, replay, how_to_explain, next_steps }`. `outcome` is always what the engine priced. `amendment` (stored quotes only; null when never touched) is `{ result, valid, sold, amended_at, log: [{ when, who, via (dashboard | api | mcp), result: { from, to }, valid, sold, note }] }`: the price, validity or sold flag someone set afterwards (dashboard, API or amend_quote), and the log of who changed what. Step names, types, descriptions and collection lookups come from the version's model when it is on this instance. A quote without a step trace is re-priced against its version (`replay: true` forces it); `replay` reports the replayed vs stored result and whether they match. Nothing is saved. Responses are kept under ~80 KB: large quotes come back clipped or as an overview (`truncated` says which) — pass `steps: [<id>, …]` for those steps in full. If even the overview is too big the result is `{ too_large: true, outcome, rules counts, next_steps }`: review a few steps at a time, or ask the user to paste the part they want explained. Explain the result back following `how_to_explain`.

    Annotations the server declares

    • readOnlyHint: true
    • idempotentHint: true
    • openWorldHint: false
  • get_quotesList quotes stored on this self-host instance, newest first (`direction: "asc"` for oldest first).No findings

    Why it is in this group

    • The name "get_quotes" says "get": a word for reading.
    Description, as the server wrote it
    List quotes stored on this self-host instance, newest first (`direction: "asc"` for oldest first). Filter by `project_reference` (from get_projects), `version_reference`, `client_ref` (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 client_ref). Paged with `limit` (default 25, max 100) and `offset`; `has_more` says whether another page exists. Returns `{ count, limit, offset, has_more, quotes: [{ quote_reference, project_reference, project_name, version_reference, version, created_at, status, valid, result, indicator, client_ref, exec_time_ms, error, amended_result, amended_valid, sold, quote_url }], next_steps }` — `result` and `valid` are what the engine priced; `amended_result` / `amended_valid` (null when not amended) are what someone changed them to in the dashboard, and `sold` (null when never set) whether it sold. No input or output payloads; call get_quote for one quote's full review. Dry runs (run_quote without save, run_version_tests) are never stored, so they never appear here; run_quote with save: true does.

    Annotations the server declares

    • readOnlyHint: true
    • idempotentHint: true
    • openWorldHint: false
  • get_schemaFetch the full JSON schema for Ptally project config files.Reads private dataNo findings

    Why it is in this group

    • The name "get_schema" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "fetch" and "file": it reads files.
    Description, as the server wrote it
    Fetch the full JSON schema for Ptally project config files. Use to check exact field requirements, allowed step types, and property constraints.

    Annotations the server declares

    • readOnlyHint: true
    • idempotentHint: true
    • openWorldHint: false
  • get_starterFetch a worked-example Ptally project for a common line of business.No findings

    Why it is in this group

    • The name "get_starter" says "get": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • idempotentHint: true
    • openWorldHint: false
  • list_docsList the documents uploaded to a project (policy wordings, product guides, underwriting guidelines or anything else), newest first, with their indexing status.Reads private dataNo findings

    Why it is in this group

    • The name "list_docs" says "list": a word for reading.

    What it can reach

    • private-dataThe name "list_docs" says "list" and "doc": it reads documents.
    • private-dataThe description's first sentence says "list" and "document": it reads documents.
    Description, as the server wrote it
    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_reference, count, indexed, pending, failed, documents: [{ document_reference, title, filename, status, error, pages, chunk_count, bytes, version_reference, created_at }], next_steps }`. `status` is `indexed` (searchable with search_docs), `pending` or `indexing` (not searchable yet), or `failed` (with the reason in `error`, e.g. a scanned PDF with no text). `chunk_count` is how many searchable passages the document has. Documents are uploaded and deleted in the dashboard, not over MCP. Nothing is changed.

    Annotations the server declares

    • readOnlyHint: true
    • idempotentHint: true
    • openWorldHint: false
  • search_docsSearch 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: wh…Reads private dataNo findings

    Why it is in this group

    • The name "search_docs" says "search": a word for reading.

    What it can reach

    • private-dataThe name "search_docs" says "search" and "doc": it reads documents.
    • private-dataThe description's first sentence says "search" and "document": it reads documents.
    Description, as the server wrote it
    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 `version_reference` (default: the latest live version, else the latest of any status; pass the version that priced a quote so the wording matches it), optional `k` (passages to return, default 5, max 20) and optional `document_references` to search only some documents. Every passage is scored by meaning (a local embedding model) and by keywords, blended 70/30. Returns `{ project_reference, version_reference, query, documents: { indexed, pending, failed }, results: [{ document_reference, title, filename, version_reference, chunk, page, section, text, score, similarity, keyword }], next_steps }`. `score` is relative to this search (the best passage scores near 1); `similarity` is the cosine similarity to the question (below about 0.5 is rarely relevant). Answer only from the returned text, citing title, section and page; read around a passage with get_doc. Nothing is changed.

    Annotations the server declares

    • readOnlyHint: true
    • idempotentHint: true
    • openWorldHint: false
  • validate_projectServer-side schema validation of a project config.No findings

    Why it is in this group

    • The name "validate_project" says "validate": a word for reading.
    Description, as the server wrote it
    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 the inline form is too large for your client); passing neither or both returns an error result.

    Annotations the server declares

    • readOnlyHint: true
    • idempotentHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.

Reads private data5
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write1
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 19, 2026, 17:22 UTC, unchanged since Nov 12, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
4
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://app.ptally.ai/.well-known/oauth-protected-resource/mcp
Authorization servers
https://app.ptally.ai
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
no
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 4 tools that change things (4 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://app.ptally.ai/mcp: tools/list returned 18 tools to an anonymous client, including amend_quote (write), run_quote (write), run_version_tests (write), patch_version (write)

    What this check looks for

Posture changes

  1. Nov 12, 2026
    • Tools that change things, listed without credentials: 3 to 4

Findings

Matches of fixed checks, with the text they matched.

1 warn2 info
  • The server marks "run_version_tests" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"idempotentHint":true,"openWorldHint":false}; The name "run_version_tests" says "run": a word for a change.

    What this check looks for
  • The description is 2,059 characters long, over the 2,000 this check looks for.

    Matched text

    description ends: "...the part they want explained. Explain the result back following `how_to_explain`."

    What this check looks for
  • The description is 3,762 characters long, over the 2,000 this check looks for.

    Matched text

    description ends: "...returned updated_at. Never approves or publishes — the user does that in the UI."

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools8 added, 2 changed.+8 added~2 changedView diff
  2. PostureRemote posture changed. Tools that change things, listed without credentials: 3 -> 4.View diff
    • Tools that change things, listed without credentials: 3 to 4

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http ptally https://app.ptally.ai/mcp
claude mcp add --transport http ptally https://app.ptally.ai/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__ptally__get_docs",
      "mcp__ptally__get_schema",
      "mcp__ptally__validate_project",
      "mcp__ptally__get_starter",
      "mcp__ptally__get_projects",
      "mcp__ptally__get_project",
      "mcp__ptally__get_quotes",
      "mcp__ptally__get_journeys",
      "mcp__ptally__get_journey",
      "mcp__ptally__get_quote",
      "mcp__ptally__list_docs",
      "mcp__ptally__search_docs",
      "mcp__ptally__get_doc",
      "mcp__ptally__get_health"
    ],
    "ask": [
      "mcp__ptally__amend_quote",
      "mcp__ptally__run_quote",
      "mcp__ptally__run_version_tests",
      "mcp__ptally__patch_version"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as ptally. Review it before you use it.

Capability tags behind 6 rules
  • mcp__ptally__get_docs private-data
  • mcp__ptally__get_schema private-data
  • mcp__ptally__get_quote untrusted-input
  • mcp__ptally__list_docs private-data
  • mcp__ptally__search_docs private-data
  • mcp__ptally__get_doc private-data

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/ai.ptally/ptally/verify?hash=b48daa6fe75ce0a744a445275904ce2522ab58e85f70cea885e3857ffc943540" | jq -e '.changed == false'

Pinned hash b48daa6fe75c, from Nov 18, 2026, 08:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/ai.ptally/ptally/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for ai.ptally/ptally
[![Anlyon Radar](https://radar.anlyon.com/badge/ai.ptally/ptally.svg)](https://radar.anlyon.com/servers/ai.ptally/ptally)

Source: MCP Registry. Synced Nov 4, 2026, 15:17 UTC.

Ptally MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Ptally MCP server safe?

No scan can promise that. What its definitions show: 18 tools, 4 of which can change, send or delete something, and 3 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Ptally MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Ptally MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the Ptally MCP server have?

18 tools: 4 write, 14 read. amend_quote, run_quote, run_version_tests, patch_version, get_docs, get_schema, validate_project, get_starter and 10 more.

Does the Ptally MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Ptally MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Ptally MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 18, 2026. Every change is on this page and in its Atom feed.