The Voiceflow Knowledge MCP is a second, separate server: where the Voiceflow MCP server works on your projects, this one knows how Voiceflow works — the product, the REST API, the vf CLI and the MCP server — and answers questions about it from the published documentation, with a citation on every answer. It is public, needs no account and no key, and changes nothing.

Connect it to any MCP client that speaks Streamable HTTP, and your assistant can answer “how do I…”, “what is…” and “does X still exist” questions about Voiceflow without leaving the conversation — or use it alongside the Voiceflow MCP server, so the assistant that edits your agent can also look up how a setting works before it changes it.

Connect a client

The server’s local name below is voiceflow-knowledge; pick any name that does not collide with a server you already have.

Run this from your terminal, not inside a Claude Code session:

Add --scope user to make it available in every project. There is no sign-in step: /mcp shows it connected straight away.

To confirm it works, check the client’s own view of the server rather than the answer: in Claude Code, /mcp lists voiceflow-knowledge as connected with its four tools; Cursor, VS Code and Codex show the server and its tools in their MCP settings. A citation alone proves nothing — an assistant with web access or prior knowledge can cite voiceflow.com/docs on its own. Then ask it how far back a Voiceflow agent remembers earlier turns and watch the call to ask_voiceflow in the transcript.

What the assistant gets

Four tools, all read-only. The assistant picks them itself; you ask in plain language.

  • ask_voiceflow — one grounded answer: the passage that answers the question, the matching facts on that page (settings, defaults, limits, prices), the concept it names, and a citation. The first call for any “how do I”, “what is”, “how does X work”, API, CLI or error question; most questions need nothing else.
  • search_voiceflow — a ranked list of pages (up to 10), each with its best matching section, a citable URL with #anchor, a snippet and why it matched. For browsing candidates, comparing two readings, or when the first answer came back weak.
  • read_voiceflow_page — one page or section as text, by URL, with its heading trail, the headings around it, and the rows of a table rendered from data. For exact wording, a code sample, a table, or a request/response schema.
  • get_voiceflow_changelog — dated changelog entries (added, improved, changed, deprecated, fixed) and tombstones: things that no longer exist, with what replaced them, each linking the page that describes the feature today. For “what’s new since”, “when did X ship”, “is X deprecated”, “does X still exist”, “what replaced X”.

The answers describe Voiceflow as it works right now. Questions about history — what changed, when, and what replaced what — belong to get_voiceflow_changelog; when the assistant asks another tool about history, the server says so and names the changelog tool.

Four resources ride alongside the tools: voiceflow://glossary (every Voiceflow term, its definition, the phrasings people use for it, and where it is documented), voiceflow://outline (where every page lives), voiceflow://skill (how to build, operate and measure agents over the APIs, the MCP server and the CLI) and voiceflow://manifest (what this deployment indexed).

How it answers well

  • The question, in the user’s words. Beside the three context fields below, question is all a call needs. The assistant may add terms in Voiceflow’s own vocabulary (a glossary term, a heading, a setting name) and an intent (how_to, what_is, api, cli, error, exact) for a sharper first call — both are optional.
  • Every call says who asked, what for, and why. Three fields are required on every tool: initiator (human — a person asked this question; agent — the assistant decided to ask it during its own task), purpose (research — exploring Voiceflow broadly; answers — a specific how-to, setting, API, CLI or error) and why (one sentence: what the caller is trying to accomplish). The assistant fills them from the tool’s schema; they tell the server nothing about who you are — no identity is sent or stored — and they are used only to understand how the server is used.
  • Weak terms are dropped, never refused. A term that is a whole sentence, a generic word, or a word the documentation never uses is dropped with a note saying so; the question is still answered.
  • The answer suggests the next call. When a call carried no terms, or the answer’s confidence is low, it comes with suggestedTerms — the nearest terms in Voiceflow’s vocabulary — so a second, sharper call needs nothing the first answer did not hand over.
  • Ask in any language. The knowledge itself is English, so the assistant is told to translate a question to English before calling and to answer in your language; a question that arrives in another language is still answered, with a note reminding the assistant to translate.
  • A URL is resolved before it is refused. read_voiceflow_page takes the shapes an assistant actually writes: the legacy docs.voiceflow.com host, a path that forgot the /docs prefix, a trailing slash, the .md twin, upper case, a page that has since moved, and an #anchor whose heading sits under a different slug. Each one reads, with a note saying what was resolved; a URL that names no page comes back with the nearest pages instead.
  • get_voiceflow_changelog takes the question itself. question, query, q, topic and subject are declared in its schema and read as about (the answer says so), and a call with no filter answers the latest changes rather than refusing.
  • Only a malformed call is refused, and the refusal says exactly how to fix it, with an example — and carries a code (no_page, no_section, bad_url, bad_since, bad_kind, unknown_field, bad_terms, wrong_tool) so a refusal can be counted by its cause.
  • Every answer carries a citation — a voiceflow.com/docs URL, with #anchor for a section — and the assistant is told to cite it verbatim.

Limits

  • Read-only, public, no sign-in. The server exposes no tool that changes anything, on Voiceflow or anywhere else.
  • Rate-limited per client address: 20 answers a minute (tool calls and resource reads), and 120 requests of any kind a minute; past either, the server answers 429 with a retry-after header. The connection handshake, the tool list and pings are not answers — a client can connect freely; only a loop pays.
  • English. The documentation is in English and the server searches it in English; an assistant translating a user’s question before asking gets the best answers.

The server was renamed on 2026-09-17 — the tools were answer_voiceflow_docs, search_voiceflow_docs, read_voiceflow_docs and changes_voiceflow_docs, and the server called itself Voiceflow Documentation. The earlier names still answer (with a note naming the new one) until version 2.2.0 of the server; update a client that uses them.

Voiceflow Documentation

    Use the up and down arrow keys to select a result, Enter to open it, and Escape to close the search.