FullStory for AI agents
FullStory is a digital experience analytics platform that captures user sessions and events to help teams understand product behavior and diagnose where users struggle. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in FullStory.
Search for a user's sessions
Search users to find the session where a customer hit a specific bug.
Check a segment's definition
Get a segment's criteria to confirm which users it currently includes.
Confirm before deleting user data
Require approval before deleting user data, since it is often tied to a privacy or compliance request.
30 FullStory actions, graded by risk.
Every FullStory action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
17Look things up. Allowed by default.
- fullstory.get_userGet User
- fullstory.get_accountGet FullStory Account
- fullstory.get_segmentGet Segment
- fullstory.search_usersSearch Users
- fullstory.get_operationGet Operation
- fullstory.list_datasetsList Datasets
- fullstory.list_segmentsList Segments
- fullstory.list_sessionsList Sessions
- fullstory.list_operationsList Operations
- fullstory.get_import_statusGet Import Status
- fullstory.get_extraction_ruleGet Extraction Rule
- fullstory.list_element_blocksList Element Blocks
- fullstory.list_import_recordsList Import Records
- fullstory.list_extraction_rulesList Extraction Rules
- fullstory.get_recording_settingsGet Recording Settings
- fullstory.get_organization_quotasGet Organization Quotas
write
7Create and change things. Allow, or ask the user first.
- fullstory.create_annotationCreate Annotation
- fullstory.create_extraction_ruleCreate Extraction Rule
- fullstory.update_extraction_ruleUpdate Extraction Rule
- fullstory.upsert_userUpsert User
- fullstory.import_usersImport Users
- fullstory.import_eventsImport Events
- fullstory.set_extraction_rule_archivedSet Extraction Rule Archived
destructive
6Delete, cancel or archive. Ask first, or deny outright.
- fullstory.cancel_operationCancel Operation
- fullstory.delete_user_dataDelete User Data
- fullstory.delete_element_blockDelete Element Block
- fullstory.get_element_blockGet Element Block
- fullstory.create_element_blockCreate Element Block
- fullstory.update_element_blockUpdate Element Block
FullStory in three steps.
- 01Your users connect FullStoryThey add their FullStory api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Annotation” can wait for the user, and “delete User Data” can be denied outright.
- 03Any agent can actYour agent calls FullStory through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('fullstory', { read: 'allow', write: 'ask', // create_annotation destructive: 'deny', // delete_user_data }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How FullStory connects.
Users add their FullStory api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same FullStory connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use FullStory from any agent.
FullStory and Arc0, answered.
Can I use FullStory with Claude, ChatGPT or Cursor?
Yes. Connect FullStory to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the FullStory actions you allow.
How do users connect FullStory?
Users add their FullStory api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which FullStory actions can my agent take?
30 in total: 17 read, 7 write and 6 destructive, such as “create Annotation”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in FullStory?
Yes. Actions like “delete User Data” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.
Can my own backend call FullStory too?
Yes. The same FullStory connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug FullStory into your agent.
Your users connect FullStory once, under your brand. Your agent gets 30 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan