Skip to content

Talkform MCP server

io.github.msanchezgrice/talkformmsanchezgricestreamable-httpv0.1.1Scanned

Collect reviewed human answers through hosted handoffs, plus local templates and config validation.

11 tools: 3 can delete or cancel things, 3 change things and 5 only read.

Tools: 3 delete, 0 irreversible, 3 write, 5 read.
  • Reads private data · 0
  • Reads text others write · 4
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

3 tools here can delete or cancel 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 Talkform MCP server can do

The Talkform MCP server is published by the GitHub account msanchezgrice. It has 11 tools. It can delete or cancel things (3 tools: talkform.delete_handoff, talkform.configure_webhook and talkform.delete_webhook) and create or change data (3 tools: talkform.prepare_form, talkform.register_agent and talkform.create_handoff). 5 tools only read.

4 tools bring in text other people can write (talkform.list_templates, talkform.register_agent, talkform.create_handoff and 1 more).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

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

Last scanned Nov 9, 2026, version 0.1.1.

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.

11 tools

Deletes or cancels 3Claude Code: deny
  • talkform.configure_webhookConfigures one HTTPS endpoint for completed handoffs in an authorized project.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Configures one HTTPS endpoint for completed handoffs in an authorized project. Replaces any active endpoint and returns the signing secret once. Requires handoffs:write permission. Optional projectId selects an owned OAuth account project.

    Annotations the server declares

    • title: Configure a completion webhook
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: true
  • talkform.delete_handoffPermanently deletes stored configuration and answers for an authorized project or OAuth account.No findings

    Why it is in this group

    • The name "talkform.delete_handoff" says "delete": a word for removing or ending something.
    • The description says "Permanently deletes".
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Permanently deletes stored configuration and answers for an authorized project or OAuth account. Requires user confirmation and handoffs:delete permission.

    Annotations the server declares

    • title: Delete a hosted interview
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: false
  • talkform.delete_webhookDisables an authorized project's active webhook and cancels pending deliveries.No findings

    Why it is in this group

    • The name "talkform.delete_webhook" says "delete": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Disables an authorized project's active webhook and cancels pending deliveries. Requires handoffs:write permission. Optional projectId selects an owned OAuth account project.

    Annotations the server declares

    • title: Disable completion webhook
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: false
Changes things 3Claude Code: ask
  • talkform.create_handoffStores a validated voice interview or text interview and returns a private respondent link plus shareText.Reads text others writeNo findings

    Why it is in this group

    • The name "talkform.create_handoff" says "create": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Stores a validated voice interview or text interview and returns a private respondent link plus shareText. config.fields[].promptTitle supplies each question; config.branding.fromName and branding.purpose identify the originating product. Omitted mode selects voice; text mode is available. Requires a project API key or scoped OAuth. Optional projectId selects an owned account project; required when the account has several projects. Matching idempotency keys replay the existing handoff.

    Annotations the server declares

    • title: Create a hosted interview
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • talkform.prepare_formTurns interview questions into a validated, shareable form draft.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.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Turns interview questions into a validated, shareable form draft. Each promptTitle is the respondent-facing question; fromName, purpose and branding identify the originating product. Optional theme colors use hex values. Returns a draft without storing or publishing it.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
    • title: Prepare a Talkform draft
  • talkform.register_agentCreates a persistent machine-owned project and returns its API key secret once.Reads text others writeNo findings

    Why it is in this group

    • The description's first verb is "create": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Creates a persistent machine-owned project and returns its API key secret once. No email, sign-in, or human identity is created. A UUIDv4 idempotency key identifies registration; retries never replay the secret. Machine projects receive 10 hosted handoffs per day. Voice is available in hosted interviews under shared realtime limits.

    Annotations the server declares

    • title: Create a private agent workspace
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Only reads 5Show 5 read-only tools
  • talkform.get_handoffChecks a hosted handoff owned by the authorized project or OAuth account.No findings

    Why it is in this group

    • The name "talkform.get_handoff" says "get": a word for reading.
    Description, as the server wrote it
    Checks a hosted handoff owned by the authorized project or OAuth account. Requires handoffs:read permission.

    Annotations the server declares

    • title: Check interview status
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • talkform.get_resultReturns completed structured answers for an authorized project or OAuth account with handoffs:read permission.No findings

    Why it is in this group

    • The name "talkform.get_result" says "get": a word for reading.
    Description, as the server wrote it
    Returns completed structured answers for an authorized project or OAuth account with handoffs:read permission. Pending results return result_pending. Results expire 7 days after submission. No transcript is returned.

    Annotations the server declares

    • title: Retrieve reviewed answers
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • talkform.get_templateReturns one public template as a structured, reviewable conversational form draft.No findings

    Why it is in this group

    • The name "talkform.get_template" says "get": a word for reading.
    Description, as the server wrote it
    Returns one public template as a structured, reviewable conversational form draft.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
    • title: Review a Talkform template
  • talkform.get_webhookReturns active webhook metadata and recent delivery metadata for an authorized project.No findings

    Why it is in this group

    • The name "talkform.get_webhook" says "get": a word for reading.
    Description, as the server wrote it
    Returns active webhook metadata and recent delivery metadata for an authorized project. Signing secrets are never returned. Requires handoffs:read permission. Optional projectId selects an owned OAuth account project.

    Annotations the server declares

    • title: Get completion webhook
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • talkform.list_templatesLists the public conversational-form templates available for review.Reads text others writeNo findings

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe description's first sentence says "list" and "review": it reads comments, which other people can write.
    Description, as the server wrote it
    Lists the public conversational-form templates available for review.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
    • title: List Talkform templates

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 private-data or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write4
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 18, 2026, 16:24 UTC, unchanged since Nov 4, 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
6
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://www.talkform.ai/.well-known/oauth-protected-resource/api/mcp
Authorization servers
https://clerk.talkform.ai
Legacy HTTP+SSE transport
no
Dynamic client registration
no
Client ID metadata documents
yes
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 6 tools that change things (3 destructive, 3 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://www.talkform.ai/api/mcp: tools/list returned 11 tools to an anonymous client, including talkform.delete_handoff (destructive), talkform.configure_webhook (destructive), talkform.delete_webhook (destructive), talkform.prepare_form (write), talkform.register_agent (write) and 1 more

    What this check looks for

Posture changes

  1. Nov 4, 2026
    • RFC 9728 protected resource metadata: none to https://www.talkform.ai/.well-known/oauth-protected-resource/api/mcp
    • Authorization servers: none to https://clerk.talkform.ai
    • Dynamic client registration: not observed to no
    • Client ID metadata documents: not observed to yes

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

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

  1. Tools11 changed.~11 changedView diff
  2. PostureRemote posture changed. RFC 9728 protected resource metadata: none -> https://www.talkform.ai/.well-known/oauth-protected-resource/api/mcp; Authorization servers: none -> https://clerk.talkform.ai; Dynamic client registration: not observed …View diff
    • RFC 9728 protected resource metadata: none to https://www.talkform.ai/.well-known/oauth-protected-resource/api/mcp
    • Authorization servers: none to https://clerk.talkform.ai
    • Dynamic client registration: not observed to no
    • Client ID metadata documents: not observed to yes

Install

Pinned to version 0.1.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http talkform https://www.talkform.ai/api/mcp
claude mcp add --transport http talkform https://www.talkform.ai/api/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__talkform__talkform_list_templates",
      "mcp__talkform__talkform_get_template",
      "mcp__talkform__talkform_get_handoff",
      "mcp__talkform__talkform_get_result",
      "mcp__talkform__talkform_get_webhook"
    ],
    "ask": [
      "mcp__talkform__talkform_prepare_form",
      "mcp__talkform__talkform_register_agent",
      "mcp__talkform__talkform_create_handoff"
    ],
    "deny": [
      "mcp__talkform__talkform_delete_handoff",
      "mcp__talkform__talkform_configure_webhook",
      "mcp__talkform__talkform_delete_webhook"
    ]
  }
}

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 talkform. Review it before you use it.

Capability tags behind 4 rules
  • mcp__talkform__talkform_list_templates untrusted-input
  • mcp__talkform__talkform_register_agent untrusted-input
  • mcp__talkform__talkform_create_handoff untrusted-input
  • mcp__talkform__talkform_configure_webhook untrusted-input

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/io.github.msanchezgrice/talkform/verify?hash=00d5eb9ea896abbb893465084d1474e686fe5545dcbaffc1251cb3de0005285a" | jq -e '.changed == false'

Pinned hash 00d5eb9ea896, from Nov 9, 2026, 16:18 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.msanchezgrice/talkform/changes.xml

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

Badge

Anlyon Radar badge for io.github.msanchezgrice/talkform
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.msanchezgrice/talkform.svg)](https://radar.anlyon.com/servers/io.github.msanchezgrice/talkform)

Source: MCP Registry · repository. Synced Oct 27, 2026, 16:18 UTC.

Talkform MCP server: questions and answers

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

Is the Talkform MCP server safe?

No scan can promise that. What its definitions show: 11 tools, 6 of which can change, send or delete something, and 0 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 Talkform MCP server delete data?

Yes. 3 tools can delete, cancel or revoke something: talkform.delete_handoff, talkform.configure_webhook and talkform.delete_webhook.

Can the Talkform 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 Talkform MCP server have?

11 tools: 3 destructive, 3 write, 5 read. talkform.delete_handoff, talkform.configure_webhook, talkform.delete_webhook, talkform.prepare_form, talkform.register_agent, talkform.create_handoff, talkform.list_templates, talkform.get_template and 3 more.

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

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

Does the Talkform MCP server send data to outside services?

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

Has the Talkform MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 9, 2026. Every change is on this page and in its Atom feed.