Lyssna MCP honesty matrix — read-only studies FAQ vs marketing that chains findings into Linear / tasks
Lyssna's MCP Help Center article (help.lyssna.com/en/articles/16071364-lyssna-mcp-server, Updated over a week ago) says you can connect Claude, ChatGPT, Microsoft 365 Copilot, Gemini, and Cursor to Lyssna research data — unmoderated tests, interviews, surveys — and ask questions grounded in what participants said. The same article is explicit: "The integration is read-only: it can answer questions grounded in your existing study data, but it can't create studies or write or edit anything back into Lyssna." FAQ: "Can MCP create or edit anything in my Lyssna account? No."
Lyssna's MCP blog (lyssna.com/blog/mcp-for-ai-research, 15 Sep 2026) goes further on action: "Build an agent that acts on findings across your other tools" — Lyssna MCP "is read-only for now – it surfaces the evidence," then "sit alongside other connected MCPs – Linear, Slack…" so "One prompt can pull a finding via Lyssna's MCP server… and create a tagged Linear ticket." They note "Lyssna isn't building these integrations directly." Feedback DevTools is honest about a different surface: first-party 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. Zero Lyssna product integration ships in FDT today.
Feedback DevTools is our product. Lyssna MCP FAQ + read-only claims from https://help.lyssna.com/en/articles/16071364-lyssna-mcp-server (Updated over a week ago); Linear/tasks marketing from https://www.lyssna.com/blog/mcp-for-ai-research/ (15 Sep 2026) — lastChecked September 29, 2026 ~4:45pm Asia/Jerusalem. Please verify before purchase.
Feedback DevTools vs Lyssna MCP
| Feedback DevTools | Lyssna MCP | |
|---|---|---|
| Positioning | Capture + create_github_issue / create_tracker_issue / mark_feedback_resolved + local-agent file:line | Research MCP — query Lyssna studies/interviews/surveys; FAQ read-only; blog markets agent + other MCPs (Linear/Slack) for tickets |
| Published MCP write surface (FAQ honesty) | create_github_issue · create_tracker_issue · mark_feedback_resolved + local-agent file:line | Read-only — "can't create studies or write or edit anything back into Lyssna"; FAQ: cannot create/edit account data; no create_github_issue / create_tracker_issue / create_pr / open_pr / codebase / git write |
| Marketing claim (tasks / Linear) | N/A — FDT ships first-party create_github_issue / create_tracker_issue; does not market "chain other MCPs" as its ticket path | Blog: "create a tagged Linear ticket" via agent + other MCPs (Linear, Slack…); "Lyssna isn't building these integrations directly" (lyssna.com/blog/mcp-for-ai-research) |
| create_github_issue / create_tracker_issue / create_pr | Yes create_github_issue / create_tracker_issue + capture-time file:line; no server-side create_pr | No — Lyssna MCP itself is read-only research query; Linear ticket would be a separate Linear MCP / agent, not a Lyssna MCP tool |
| Server-side auto-open / auto-merge PRs | No — we do not claim server-side auto PRs | No — FAQ + blog frame read-only evidence surfacing; Lyssna MCP does not open or merge GitHub PRs |
| Source maps / file:line | Yes — capture-time React component + file:line | Study details, structure, responses, transcripts, interview summaries — research evidence, not React component file:line |
| Lyssna in FDT today | Zero — no Lyssna product integration ships in Feedback DevTools today | First-party remote MCP into Lyssna research (mcp.lyssna.com/mcp) on paid plans |
| Plan gate | Free plan forever + Pro $9/mo per project — MCP tools without a research-suite Enterprise SKU | All paid Lyssna plans (Help Center); not a separate $9 MCP SKU |
Lyssna MCP read-only FAQ verified on help.lyssna.com/en/articles/16071364-lyssna-mcp-server (Updated over a week ago); Linear/tasks agent marketing verified on lyssna.com/blog/mcp-for-ai-research (15 Sep 2026) — lastChecked September 29, 2026 ~4:45pm Asia/Jerusalem
Where Lyssna MCP is genuinely strong
Credit where due — Lyssna MCP is a real research unlock if:
- You already run Lyssna unmoderated tests, surveys, and interviews and want Claude / ChatGPT / Copilot / Cursor / Gemini to query studies, transcripts, quotes, and cross-study themes without exporting.
- Workspace permissions + OAuth matter more than React component file:line — access follows existing Lyssna permissions.
- Semantic search across interview transcripts, recording transcripts, and written answers in your own words is the primary surface.
Where Feedback DevTools is more honest about create_* / ship
- Marketing vs FAQ. Blog (lyssna.com/blog/mcp-for-ai-research) markets turning findings into Linear tickets via other MCP servers in an agent you build; Help Center FAQ (Updated over a week ago) is explicit that Lyssna MCP is read-only and cannot create/edit studies (lastChecked September 29, 2026 ~4:45pm 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. Lyssna's published MCP surface queries research evidence — a Linear ticket, if any, is a separate Linear MCP / agent using Lyssna context, not a Lyssna MCP write tool.
- Local-agent path. The same context is handed to your coding agent; a PR, if any, is that agent's git workflow — not a Lyssna 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 study ID or quote alone.
- Zero Lyssna in FDT today. This foil is honesty about surfaces — Feedback DevTools does not ship a Lyssna connector; it ships create_github_issue / create_tracker_issue + local-agent file:line.
Pricing shape (not the foil) (as of September 29, 2026)
- Lyssna: paid plans with MCP available on all paid plans (sources: help.lyssna.com/en/articles/16071364-lyssna-mcp-server; lyssna.com/blog/mcp-for-ai-research)
- 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 Lyssna as a research suite with a read-only MCP connector (Linear/tasks via other MCPs in an agent you build).
Who should pick which?
- Choose Lyssna MCP if your evidence archive is Lyssna studies/interviews/surveys and you want AI assistants to query that research read-only — then optionally chain other MCPs (Linear, Slack) yourself for tickets.
- Choose Feedback DevTools if you want visual feedback with file:line on capture, first-party MCP tools that create GitHub/Linear tickets (create_github_issue / create_tracker_issue), and a local-agent fix path — without reading "create a tagged Linear ticket" agent-chain marketing as a published Lyssna MCP write tool.
Frequently asked questions
What does Lyssna MCP FAQ say about create/edit?
Per https://help.lyssna.com/en/articles/16071364-lyssna-mcp-server (Updated over a week ago; lastChecked September 29, 2026 ~4:45pm Asia/Jerusalem): "The integration is read-only: it can answer questions grounded in your existing study data, but it can't create studies or write or edit anything back into Lyssna." FAQ answer: "Can MCP create or edit anything in my Lyssna account? No."
What does Lyssna market about Linear / tasks?
Per https://www.lyssna.com/blog/mcp-for-ai-research/ (15 Sep 2026): "Lyssna's MCP server is read-only for now – it surfaces the evidence. But in an agent you build yourself, it can sit alongside other connected MCPs – Linear, Slack…" so one prompt can "create a tagged Linear ticket." They state "Lyssna isn't building these integrations directly."
Can Lyssna MCP create GitHub issues, Linear tickets, or pull requests?
No create_github_issue / create_tracker_issue / create_pr / open_pr / codebase / git write tool on the Lyssna MCP surface — FAQ is read-only (help.lyssna.com/en/articles/16071364-lyssna-mcp-server; lastChecked September 29, 2026 ~4:45pm Asia/Jerusalem). A Linear ticket or GitHub PR, if any, is a separate MCP / coding agent using Lyssna context — not Lyssna MCP itself. Feedback DevTools foils with create_github_issue / create_tracker_issue + local-agent path and does not claim server-side auto-open or auto-merge. Distinct from Pendo#80 / Contentsquare#79 / Dovetail#78 / FullStory#77 / Maze#73.
Try Feedback DevTools free — create_github_issue / create_tracker_issue with file:line, no server-side auto-PR or "chain other MCPs for Linear" as the ticket path.