FullStory MCP honesty matrix — agentic "fix the friction" marketing vs read-only generate_session_summary / generate_context
FullStory's MCP launch blog (fullstory.com/blog/fullstory-mcp) positions an agentic workspace: the MCP server "doesn't just answer questions; it optimizes experiences," and upcoming capabilities will "allow your AI agent to quickly fix the friction or optimize the experience."
The published Fullstory for Customer Agents MCP Integration docs list exactly two tools at https://api.fullstory.com/mcp/activations — generate_session_summary and generate_context. The FAQ states: "Read-only: This server does not create or modify Fullstory configuration. It returns summaries and context only." There is no create_pr / open_pr / codebase / git write / ship tool. Feedback DevTools is honest about a different surface: create_github_issue / create_tracker_issue / mark_feedback_resolved plus source-mapped local-agent context with file:line. We do not claim server-side auto-opened or auto-merged PRs.
Feedback DevTools is our product. FullStory MCP blog marketing from https://www.fullstory.com/blog/fullstory-mcp/; published tools + Read-only FAQ from https://help.fullstory.com/hc/en-us/articles/40638097247639-Fullstory-for-Customer-Agents-MCP-Integration — lastChecked September 29, 2026 ~8:25am Asia/Jerusalem. Please verify before purchase.
Feedback DevTools vs FullStory MCP
| Feedback DevTools | FullStory MCP | |
|---|---|---|
| Positioning | Capture + create_github_issue / create_tracker_issue / mark_feedback_resolved + local-agent file:line | Session replay / behavioral context MCP — blog markets agentic "fix the friction"; docs are Customer Agents summaries + context |
| Published MCP tools | create_github_issue · create_tracker_issue · mark_feedback_resolved + local-agent file:line | generate_session_summary · generate_context only (api.fullstory.com/mcp/activations) — no create_pr / ship |
| Blog agentic claim | N/A — FDT does not market agentic auto-fix; create_* tickets + local-agent path | "doesn't just answer questions; it optimizes experiences" / "fix the friction" (fullstory.com/blog/fullstory-mcp) |
| Docs Read-only FAQ | create_* writes tickets (not FullStory config); local agent applies fix | "Read-only: This server does not create or modify Fullstory configuration. It returns summaries and context only." |
| create_pr / open_pr / codebase / git write | No — create_github_issue + local-agent fix path (Cursor/Claude opens a PR if you ask; not a FullStory MCP PR tool) | No dedicated create_pr / open_pr / codebase / git write / ship tool |
| Server-side auto-open / auto-merge PRs | No — we do not claim server-side auto PRs | No — published tools return summaries and context only |
| Source maps / file:line | Yes — capture-time React component + file:line | Session summaries / structured context — behavioral journey, not React component file:line |
| Pricing shape | Unlimited free collection; Pro $9/mo per project | FullStory Enterprise/Advanced + Activations quota; MCP connector, not a separate $9 MCP SKU |
FullStory MCP blog quotes verified on fullstory.com/blog/fullstory-mcp; tools + Read-only FAQ on help.fullstory.com/hc/en-us/articles/40638097247639-Fullstory-for-Customer-Agents-MCP-Integration — lastChecked September 29, 2026 ~8:25am Asia/Jerusalem
Where FullStory MCP is genuinely strong
Credit where due — FullStory Customer Agents MCP is a real session-context unlock if:
- You already capture FullStory sessions and want AI support / sales / CX agents to pull generate_session_summary or generate_context on demand.
- OAuth 2.1 Activation-scoped access at api.fullstory.com/mcp/activations matches your privacy and masking rules.
- Pre-call briefings, ticket auto-enrichment, and live behavioral grounding matter more than opening a GitHub PR from MCP.
Where Feedback DevTools is more honest about create_* / ship
- Blog vs docs. fullstory.com/blog/fullstory-mcp markets agentic MCP that "optimizes experiences" and lets agents "fix the friction"; Customer Agents docs publish only generate_session_summary + generate_context and FAQ "Read-only… summaries and context only" (lastChecked September 29, 2026 ~8:25am Asia/Jerusalem). We quote both so buyers are not surprised.
- Tickets with file:line. create_github_issue and create_tracker_issue open GitHub/Linear tickets whose bodies carry component + file:line from capture. FullStory's published Customer Agents surface has no create_github_issue / create_pr / ship equivalent — it returns session summaries and structured context.
- Local-agent path. The same context is handed to your coding agent; a PR, if any, is that agent's git workflow — not a FullStory MCP PR tool. FDT does not claim server-side auto-open or auto-merge.
- Capture-time source maps. Every item pins the React component and file path:line so the agent starts from a known path instead of rediscovering from a session summary alone.
- Pricing shape. Unlimited free collection; Pro is $9/mo per project.
Pricing shape (not the foil) (as of September 29, 2026)
- FullStory: Enterprise/Advanced + Activations; Customer Agents MCP at api.fullstory.com/mcp/activations (sources: fullstory.com/blog/fullstory-mcp; help.fullstory.com …40638097247639…)
- Feedback DevTools: Free (unlimited collection) · Pro $9/mo per project (source: feedback-devtools.com/pricing)
MCP honesty is about capability claims, not sticker shock — FDT Pro is $9/mo per project vs FullStory as a full digital-experience suite with MCP as a session-context connector.
Who should pick which?
- Choose FullStory Customer Agents MCP if your evidence archive is FullStory sessions and you want AI agents to pull generate_session_summary / generate_context for support, sales, or CX grounding.
- Choose Feedback DevTools if you want visual feedback with file:line on capture, MCP tools that create GitHub/Linear tickets (create_github_issue / create_tracker_issue), and a local-agent fix path — without reading blog "fix the friction" copy as a published create_pr / ship tool.
Frequently asked questions
What does the FullStory MCP blog claim about agentic optimization?
Per https://www.fullstory.com/blog/fullstory-mcp (lastChecked September 29, 2026 ~8:25am Asia/Jerusalem): FullStory is "aggressively building toward an agentic workspace where the Fullstory MCP server doesn't just answer questions; it optimizes experiences," including capabilities that "allow your AI agent to quickly fix the friction or optimize the experience."
Which tools does Fullstory for Customer Agents MCP publish?
Per https://help.fullstory.com/hc/en-us/articles/40638097247639-Fullstory-for-Customer-Agents-MCP-Integration: generate_session_summary and generate_context at https://api.fullstory.com/mcp/activations. FAQ current limitations: "Read-only: This server does not create or modify Fullstory configuration. It returns summaries and context only."
Does FullStory MCP create pull requests or ship code fixes?
No create_pr / open_pr / codebase / git write / ship tool is on the published Customer Agents tool list (lastChecked September 29, 2026 ~8:25am Asia/Jerusalem). A PR or code fix, if any, is the coding agent using FullStory session context — not those MCP tools. Feedback DevTools foils with create_github_issue / create_tracker_issue + local-agent path and does not claim server-side auto-open or auto-merge.
Try Feedback DevTools free — create_github_issue / create_tracker_issue with file:line, no server-side auto-PR or "fix the friction" MCP claims.