Skip to content

Use AI to manage your submissions.

Point your assistant at your workspace and let it triage spam, draft replies, and audit integrations.

Things people ask for out loud

  • “Summarize this week’s leads.”
  • “Find spam that slipped through.”
  • “Draft replies for new inquiries.”
  • “Group feedback into bugs, feature requests, and support issues.”
  • “Tell me which forms are underperforming.”
  • “Show me failed integrations.”
Tools
134
Mutating actions across forms, submissions, webhooks, billing, insights, tokens.
Resources
21
Read-only URIs the agent can subscribe to.
Prompts
12
Turn-key playbooks: triage, audit, draft, summarize.
Abilities
49
Mint a token with exactly the abilities the agent needs, no more.
Pricing
Every plan
Bundled on every plan; funnels and surveys on Pro and above. No per-call charges.
Why AI workflows

An assistant that can help run your submissions, not just talk about them.

MCP lets agents read your inbox, mark spam, draft autoresponders, audit webhooks, and propose configuration changes from inside your editor or agent runtime. No glue code, no sync jobs, no screen scraping.

Triage from anywhere

Ask your agent to review spam, mark false positives, and patch custom rules in one chat session.

Draft like a teammate

Give the agent a form intent and let it draft autoresponder copy, propose new fields, or test-send before publishing.

Scoped by default

Every token carries an explicit ability list. Read-only, spam triage, webhook replay, or form editing stays under your control.

Same shape as the API

Tools mirror the REST API. If you can do it in the dashboard or API, an approved agent can help with it.

Webhooks as a conversation

Audit recent deliveries, replay failures, and update destinations without leaving your editor.

Documented surface

Every tool, ability, resource, prompt, and error shape is documented for technical review.

Install

Install Formspring on your agent.

Use the official Cursor and Claude Code plugins for skills and slash commands, or paste HTTP MCP config into any supported client. The setup wizard generates a token-specific snippet per client.

Plugins are the short path:formspring-ai bundles MCP, product-routing rules, and commands for Cursor and Claude Code. Every other client uses the same bearer token against https://formspring.io/mcp-server.

Pick your client
# Recommended: Formspring plugin (MCP + skills + commands)
# Cursor marketplace, or team import:
#   https://github.com/formspring-io/formspring-ai

export FORMSPRING_TOKEN="your-api-token"
# Reload Cursor after install (Developer: Reload Window)

# Manual MCP only (.cursor/mcp.json or ~/.cursor/mcp.json):
{
  "mcpServers": {
    "formspring": {
      "url": "https://formspring.io/mcp-server",
      "headers": { "Authorization": "Bearer your-api-token" }
    }
  }
}

Mint a token on your account API page, or let the setup wizard write the config for you.

Catalog

134 tools. 21 resources. 12 prompts.

Tools mutate. Resources are read-only views with stable URIs. Prompts are turn-key playbooks the agent runs end-to-end. Every entry lists the ability it requires.

Forms

  • list_forms
  • get_form
  • create_form
  • update_form
  • set_form_document
  • publish_form
  • unpublish_form
  • archive_form
  • restore_form
  • send_test_autoresponder
  • send_test_notification

Templates

  • list_templates

Submissions

  • list_submissions
  • get_submission
  • update_submission
  • delete_submission
  • bulk_submissions
  • export_submissions
  • get_submission_file
  • mark_as_spam
  • get_form_stats

Webhooks

  • list_webhooks
  • get_webhook
  • create_webhook
  • update_webhook
  • delete_webhook
  • list_webhook_deliveries
  • replay_webhook_delivery

Surveys

  • list_surveys
  • get_survey
  • create_survey
  • update_survey
  • set_survey_document
  • publish_survey
  • unpublish_survey
  • delete_survey
  • get_survey_insights
  • regenerate_survey_insights

Polls

  • list_polls
  • get_poll
  • create_poll
  • update_poll
  • set_poll_document
  • publish_poll
  • unpublish_poll
  • get_poll_results

Feedback

  • list_feedback_boards
  • create_feedback_board
  • list_feedback_posts
  • create_feedback_post
  • update_feedback_post_status
  • publish_feedback_announcement

Response Desk

  • list_desk_threads
  • assign_desk_thread
  • resolve_desk_thread
  • reply_desk_thread

Action classes

  • list_action_classes
  • get_action_class
  • create_action_class
  • update_action_class
  • delete_action_class
  • attach_survey_trigger
  • detach_survey_trigger

Contacts

  • list_contacts
  • get_contact
  • create_contact
  • update_contact
  • delete_contact

Segments

  • list_segments
  • get_segment
  • create_segment
  • update_segment
  • delete_segment
  • assign_survey_segment
  • unassign_survey_segment

SDK keys

  • list_sdk_keys
  • get_sdk_key
  • create_sdk_key
  • update_sdk_key
  • revoke_sdk_key

Displays (read-only)

  • list_displays
  • get_display
  • get_survey_display_analytics

Funnels

  • list_funnels
  • get_funnel
  • create_funnel
  • update_funnel
  • set_funnel_document
  • publish_funnel
  • delete_funnel
  • get_funnel_analytics
  • list_funnel_sessions
  • add_screen
  • add_block
  • set_logic
  • set_score
  • set_pixel
  • set_capi_token

Links

  • list_links
  • get_link
  • create_link
  • update_link
  • delete_link

Bio pages (link-in-bio)

  • list_bio_pages
  • get_bio_page
  • create_bio_page
  • update_bio_page
  • set_bio_document
  • set_bio_pixel
  • add_bio_block
  • reorder_bio_blocks
  • delete_bio_block
  • delete_bio_page

Automations

  • list_automations
  • get_automation
  • create_automation
  • update_automation
  • enable_automation
  • disable_automation
  • run_automation
  • list_automation_runs
  • get_automation_run
  • replay_automation_run
  • delete_automation

Billing (read-only)

  • get_team
  • get_plan
  • get_usage
  • get_subscription_state

AI Insights

  • get_ai_insights
  • regenerate_ai_insights

Tokens (self-management)

  • list_tokens
  • create_token
  • revoke_token

Integration reference

  • get_framework_integration_catalog

Read-only views with stable URIs.

formspring://team/forms
List of active forms
formspring://docs/framework-integrations
Pointer to framework integration catalog tool
formspring://forms/{public_id}
Single form
formspring://forms/{public_id}/submissions/recent
Last 25 inbox submissions
formspring://forms/{public_id}/stats
30-day stats
formspring://forms/{public_id}/insights
Latest AI digest
formspring://team/usage
Current period usage
formspring://team/plan
Plan, features, limits
formspring://webhooks/{webhook_id}
Single webhook
formspring://webhooks/{webhook_id}/deliveries/recent
Last 50 deliveries
formspring://team/surveys
List of active surveys
formspring://surveys/{public_id}
Single survey
formspring://surveys/{public_id}/stats
30-day survey response totals
formspring://team/funnels
List of active funnels
formspring://funnels/{slug}
Single funnel
formspring://funnels/{slug}/analytics
Funnel sessions & conversion summary
formspring://team/links
Recent short links
formspring://links/{slug}
Single short link
formspring://team/automations
All automations across forms/surveys/funnels
formspring://automations/{id}
Single automation with steps
formspring://automations/{id}/runs/recent
Last 50 automation runs

Turn-key playbooks the agent runs end-to-end.

triage-spam
Review spam, propose corrective rules
summarize-week
Last-7-day exec summary for a form
draft-autoresponder
Draft + test + confirm before saving
audit-webhooks
Bucket failures, propose patches
categorize-submissions
Apply taxonomy via update_submission
draft-form
Sketch a new form schema, then create_form
weekly-digest-brief
Read team digest, recommend actions
integration-health
Per-team webhook health card
draft-survey
Sketch a multi-screen survey, then create_survey
funnel-conversion-review
Diagnose funnel drop-off, propose A/B-friendly fixes
link-traffic-snapshot
Top-N click volume, expiring/disabled links
automation-failure-audit
Bucket failed runs, propose replay/update/disable

One sentence to your agent. One tool call to your forms.

Copy any of these into your agent. They work as-is; replace the form name with one of yours.

More in the prompt examples doc.

  1. Triage spam

    submissions:read · submissions:write

    “Triage today's spam folder for the Contact form. Walk me through each submission, decide keep / mark not-spam / delete, and apply via bulk_submissions when I confirm.”

  2. Audit webhooks

    webhooks:read · webhooks:write

    “Audit every webhook on every form. For each, check the last 100 deliveries. Tell me which are unhealthy and why. Sort the report worst-first.”

  3. Draft autoresponder

    forms:read · forms:test-email · forms:write

    “Draft an autoresponder for the Contact form. Friendly tone. Mention our 24-hour response window. Send a test to my account email, but don’t save until I confirm.”

  4. Weekly digest

    submissions:read · insights:read

    “Build me a weekly digest for the Contact form. One headline number, spam ratio movement vs. last week, top 3 themes, one outlier. Markdown, ready to paste into email.”

  5. Categorize backlog

    submissions:read · submissions:write

    “Re-categorize every uncategorized submission on the Contact form from the last 30 days. Use the form’s existing categories. Show me 5 sample decisions before applying the rest.”

  6. Health check

    forms:read · webhooks:read

    “Run an integration health check across the team. Flag every form whose autoresponder is enabled but hasn’t fired, and every webhook with <90% success rate.”

Tokens are the fence.

Tokens are scoped, ability-gated, and team-isolated. Agents only see what your token allows. Revoke any time from the API page.

  1. Scoping

    Every tool checks the token has the right ability. No ability, no call.

  2. Team isolation

    Tokens are minted in a single team. Cross-team reads return not found.

  3. Revocable

    Pull a token in one click. Agents lose access immediately on the next call.

Wire your agent into your forms in under five minutes.

Mint a scoped token, paste one config block, and ask your assistant to triage, draft, and audit for you.

Scoped, ability-gated, and isolated to one workspace.