For developers

Your AI agent already speaks Unfold.

Create structured plans, distribute them via claim links, and track progress -- all from your AI agent. Four lines of config.

mcp.json

{
  "mcpServers": {
    "unfold": {
      "command": "npx",
      "args": ["@anthropic/unfold-mcp-server"],
      "env": { "UNFOLD_API_KEY": "unfold_sk_..." }
    }
  }
}

Works with Claude Code, Cursor, Windsurf, and any MCP client.

Claude Code

>Create a Python certification learning path for our new data team. 8 modules, 12 weeks. Generate claim links for each of the 6 team members.

Your AI agent. Their growth.

create_goal

Create a goal with AI-generated plan. Agent auto-answers clarification questions using context you provide. Set auto_respond=false to review agent suggestions first.

Inputtitle, description, context?, auto_respond?, priority

Outputgoal_id, claim_link, progress_link, questions?, agent_answers_used?

get_goal_status

Check progress: completion %, steps done, blockers, who claimed it. Includes agent answer transparency when plan is ready.

Inputgoal_id

Outputprogress, steps[], assigned_to, agent_answers_used?

get_clarification

Get pending clarification questions with agent-suggested answers and confidence levels. Use after create_goal with auto_respond=false.

Inputgoal_id

Outputquestions[], agent_answer, agent_confidence, agent_source

submit_clarification

Submit your answers to clarification questions. Accept agent suggestions for the rest, or override any answer.

Inputgoal_id, answers?, accept_agent_answers?

Outputgoal_id, status, agent_answers_used[]

import_plan

Import pre-formulated steps from Jira, Linear, or your own tool. AI enriches with dependencies, durations, severity, and critical path.

Inputtitle, steps[], enrich?, enrich_options?

Outputgoal_id, plan_id, enriched_steps[], claim_link

list_goals

See all goals in your org. Filter by status or claim state.

Inputstatus?, claim_status?, limit?, offset?

Outputgoals[], total_count

revoke_claim

Invalidate a claim link. Already-claimed goals are not affected.

Inputclaim_token

Outputsuccess, message

“Create an onboarding plan for our new hire starting Monday and email them the claim link”

Team onboarding

“Import our Jira sprint backlog as a goal with dependencies and time estimates”

Plan import + enrichment

“Create a 12-week coaching plan for Sarah with weekly reflection steps”

Coaching at scale

“Create a Python learning path but let me review the questions before generating the plan”

Semi-auto with review

“How many learners have completed the Python certification path?”

Academy tracking

“List all unclaimed goals in our org that are older than 7 days”

Operations

Prefer REST? We have that too.

All MCP tools map to REST endpoints. Authenticate with your API key as a Bearer token.

POST/api/v1/ext/goals/unfoldCreate goal with agent-assisted plan generation

POST/api/v1/ext/goals/importImport steps with AI enrichment

POST/api/v1/ext/goals/:id/clarify/submit-allSubmit clarification answers

GET/api/v1/ext/goals/:idGet goal status, progress & agent answers

GET/api/v1/ext/goalsList org goals (paginated)

DELETE/api/v1/ext/goals/claims/:tokenRevoke a claim link

Example

curl -X POST https://api.unfoldit.ai/api/v1/ext/goals/unfold \
  -H "Authorization: Bearer unfold_sk_..." \
  -H "Content-Type: application/json" \
  -d '{
    "title": "Python Certification",
    "autoRespond": true,
    "context": { "experienceLevel": "beginner", "timeline": "12 weeks" }
  }'

AuthBearer token (unfold_sk_...)

Rate limit100 req/min per key

Scopesgoals:create, goals:read, claims:manage

Get started

1Create an organization in Unfold

2Generate an API key in Settings

3Add the MCP config to your AI agent

4Start creating goals

Your AI agent already speaks Unfold.

What your AI agent can do

Available tools

What you say to your AI agent

Prefer REST? We have that too.

Get started