Talkform
Server Details
Collect reviewed human answers through hosted handoffs, plus local templates and config validation.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- msanchezgrice/audioform
- GitHub Stars
- 0
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 11 tools
Most tools target clearly distinct resources: handoffs, webhooks, templates, results, and agent registration. The main potential confusion is between get_handoff (checking a hosted handoff) and get_result (retrieving completed answers), plus prepare_form versus create_handoff, though the descriptions provide enough detail to separate them.
All tools use a consistent talkform.<verb>_<noun> snake_case pattern, including configure_webhook, create_handoff, get_result, list_templates, and register_agent. There are no mixed casing or naming-style deviations.
The 11 tools are well-scoped for a domain covering handoff lifecycle, webhooks, templates, results, and agent registration. Each tool earns its place, and the count stays within a manageable range.
The set covers create/get/delete for handoffs, full webhook management, template retrieval, result fetching, and agent registration. However, there is no list_handoffs or list_results operation, which could make enumeration and recovery of known handoffs harder, though core workflows remain possible.
Available Tools
11 toolstalkform.configure_webhookConfigure a completion webhookADestructiveInspect
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.
Inputs: url (required), projectId.
talkform.create_handoffCreate a hosted interviewAIdempotentInspect
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.
Inputs: config (required), idempotencyKey (required), projectId.
talkform.delete_handoffDelete a hosted interviewADestructiveIdempotentInspect
Permanently deletes stored configuration and answers for an authorized project or OAuth account. Requires user confirmation and handoffs:delete permission.
Inputs: id (required).
talkform.delete_webhookDisable completion webhookADestructiveIdempotentInspect
Disables an authorized project's active webhook and cancels pending deliveries. Requires handoffs:write permission. Optional projectId selects an owned OAuth account project.
Inputs: projectId.
talkform.get_handoffCheck interview statusCRead-onlyIdempotentInspect
Checks a hosted handoff owned by the authorized project or OAuth account. Requires handoffs:read permission.
Inputs: id (required).
talkform.get_resultRetrieve reviewed answersARead-onlyIdempotentInspect
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.
Inputs: id (required).
talkform.get_templateReview a Talkform templateARead-onlyInspect
Returns one public template as a structured, reviewable conversational form draft.
Inputs: id (required). Returns: draft, preview
talkform.get_webhookGet completion webhookARead-onlyIdempotentInspect
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.
Inputs: projectId.
talkform.list_templatesList Talkform templatesARead-onlyInspect
Lists the public conversational-form templates available for review.
Inputs: no named parameters. Returns: templates
talkform.prepare_formPrepare a Talkform draftARead-onlyInspect
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.
Inputs: title (required), fields (required), mode, theme, +5 more. Returns: draft, preview
talkform.register_agentCreate a private agent workspaceAIdempotentInspect
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.
Inputs: idempotencyKey (required), name, environment.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Human-in-the-loop document extraction: submit a doc, get validated fields and an audit trail.
Create surveys, feedback and classification campaigns. Collect human answers and export results.
Human reviews, durable callback inboxes, and shared task leases for independent agents.
Publish live pages from any agent, collect what visitors submit, and read it back.
Related MCP Servers
- AlicenseAqualityCmaintenanceReal human judgment as agent tools -- an AI agent can ask a question and get back a structured, schema-validated JSON answer from a real quality-scored human. 16 response types (yes/no, ratings, rankings, A/B tests, sentiment, image/video/audio review, voice/video/photo capture). Fully programmatic signup with a $5 free trial credit, no card required.747 npmMIT
- AlicenseAqualityFmaintenanceFeedback collection for AI agents. Create surveys from JSON schema, collect responses from groups of people, and retrieve structured results.51MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to submit work to real human reviewers, receive pinned feedback and approval verdicts, and iterate until the output is signed off.38 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to submit work for human review over MCP or REST, then retrieve approvals, edits, or change requests without blocking. Reviewers can approve, edit, or send back items from a web or phone interface.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.