Dovetail
Dovetail is an Australian software company that provides tools for transcription analysis, coding interpretation of interviews, survey responses, and feedback, enabling users to create summarized insights from their research analysis.
Verdict
Common use cases
- Log customer quotes during support calls
- File research insights from Slack threads
- Create interview contacts before scheduling
- Tag feedback themes as tickets arrive
- Retrieve note details for synthesis sessions
Integration
- Vendor
- Dovetail
- Category
- developer-tools
- Auth
- API_KEY
- Tools
- 18
- Composio slug
dovetail
Tools
- Create Channel
Tool to create a new channel in dovetail. use after confirming channel details.
- Create Contact
Tool to create a new contact in dovetail. use when you need to register a contact before logging interactions.
- Create Data Point
Tool to create a data point within a channel. use after capturing new content to record and classify it in dovetail.
- Create Insight
Tool to create a new insight in dovetail. use after synthesizing findings when ready to store them. example: "create insight 'q1 user trends' with body '...' for project 'proj 123'."
- Create Topic
Tool to create a new topic in a channel. use after confirming channel id, title, and optional description.
- Delete Channeldestructive
Tool to delete an existing channel. use when you need to remove a channel and move it to the project's trash (restorable for 30 days). confirm the channel id before calling.
- Delete Topicdestructive
Tool to delete an existing topic. use when you have confirmed the topic id and want to move it to trash (restorable for 30 days). example: "delete topic with id 123e4567-e89b-12d3-a456-426614174000."
- Get Note
Tool to retrieve details of a specific note. use when you have confirmed the note id and need full note metadata from dovetail.
- Get Token Info
Tool to get information about the current api token. use after authenticating to verify token scopes and expiry.
- List Contacts
Tool to list all contacts in dovetail. use after authenticating with a valid workspace token when you need the complete contact list.
- List Data
Tool to list data items in dovetail. use when you need to retrieve, filter, sort, or paginate through your workspace data after authentication. supports dovetail filters, sort syntax, and cursor-based pagination.
- List Highlights
Tool to list all highlights in dovetail. use after authenticating with a valid workspace token when you need to retrieve the complete highlight list.
- List Notes
Tool to list all notes in dovetail. use after confirming you have a valid workspace token and need to retrieve the full note list.
- List Projects
Tool to list all projects in dovetail. use after authenticating with a valid workspace token when you need to retrieve the full project list.
- List Tags
Tool to list all tags in dovetail. use after authenticating with a valid workspace token when you need to retrieve the complete tag list.
- List User Insights
Tool to list insights for a specific user. use when you need to retrieve all personal insights associated with a user id.
- Magic Search
Tool to perform a magic search across workspace data. use when you need to retrieve relevant highlights, notes, insights, channels, themes, or tags by query.
- Update Topic
Tool to update an existing topic. use after confirming the topic id and fields to change. example: "update topic with id 123... to have title 'new'".
Setup
Setup guide
- 11. In Switchy, open Settings and navigate to Integrations. 2. Find Dovetail in the MCP directory and click Connect. 3. You'll be prompted to enter a Dovetail API key — generate one by logging into Dovetail, going to Settings > API Keys, and creating a new key with read and write permissions. 4. Paste the key into Switchy and click Authorize. 5. Switchy confirms the connection and shows which projects the key can access. 6. Open any Space, type '@Dovetail create insight' followed by your finding, and send the message. 7. Dovetail responds with the insight ID and a link to view it in your repository. 8. If the tool returns an error about missing project ID, check that your API key has access to the project you're targeting.
What teammates see: by default, memories from Dovetail are scoped to the Space (PROJECT visibility) - you can mark any memory PRIVATE or share it ORG-wide.
Works well with
Top models
Compatibility data appears once enough Spaces have used this MCP together with a given model.
How Switchy teams use it
Starter prompts
Log Customer Feedback
@Dovetail create insight titled 'Onboarding friction' with body 'User reported confusion during SSO setup — expected auto-redirect but saw manual login form' for project ID proj_abc123.Open in a Space →
Register Interview Contact
@Dovetail create contact with name 'Alex Chen', email 'alex@example.com', and role 'Product Manager' in project proj_abc123.Open in a Space →
Start Feedback Channel
@Dovetail create channel named 'Mobile App Feedback' with description 'User reports and feature requests from iOS and Android' in project proj_abc123.Open in a Space →
Retrieve Note Details
@Dovetail get note with ID note_xyz789 and show me the title, tags, and transcript excerpt.Open in a Space →
Tag Emerging Theme
@Dovetail create topic titled 'Pricing concerns' in channel chan_def456 with description 'Mentions of cost as a barrier to upgrade'.Open in a Space →
Example outputs
Illustrative - representative of the model's voice and quality, not literal recordings.
@Dovetail list all insights from our Q1 user research project and group them by the most common themes
Based on the Q1 user research project (ID: proj_8x2k), I found 47 insights across 3 primary themes: **Onboarding friction** (18 insights): Users consistently report confusion during initial setup, particularly around API key configuration and workspace permissions. **Feature discovery** (16 insights): Teams struggle to find advanced filtering options; most rely on basic search despite richer tools being available. **Collaboration gaps** (13 insights): Async feedback loops break down when stakeholders can't comment directly on tagged data points. This synthesis draws from insights created between Jan 3–Mar 28. Each theme links back to the underlying data points and interview transcripts in your Dovetail workspace.
This example shows how the MCP pairs read access (fetching insights) with the AI's reasoning to surface patterns. Requires read permissions on the target project. The grouping logic happens in the AI layer—Dovetail returns raw insight records, not pre-clustered themes.
@Dovetail create a new insight titled 'Mobile nav redesign needed' summarizing feedback from the last 5 user interviews, and tag it with 'high-priority'
Created insight **'Mobile nav redesign needed'** (ID: ins_9k4m) in your workspace. **Body excerpt**: "Across interviews with users U-042 through U-046, 4 of 5 participants abandoned tasks when the hamburger menu failed to surface the 'Export' action. Average time-to-frustration: 38 seconds. Recommendation: promote top 3 actions to persistent bottom nav." Tagged as `high-priority`. This insight is now visible to your team in the project dashboard and can be linked to design tickets or roadmap items in your connected tools.
Demonstrates the MCP's write capability—creating structured research artifacts from conversational input. The AI drafts the insight body by synthesizing context you provide (or from earlier messages). You'll need write permissions on the target project. Side-effect: this insight is immediately visible to all project collaborators.
@Dovetail pull the 10 most recent data points from our 'Customer feedback' channel and draft a one-page summary for the product team
Retrieved 10 data points from the **'Customer feedback'** channel (last updated Apr 12). Here's a summary: **Top requests** (6 mentions): Bulk export to CSV, dark mode for mobile app, Slack notification customization. **Pain points** (3 mentions): Slow load times on datasets >500 rows, unclear error messages during file uploads. **Praise** (1 mention): New tagging UI described as "finally intuitive." **Recommended next steps**: Prioritize bulk export (requested by enterprise accounts). Investigate performance bottleneck flagged in data points DP-1823, DP-1829. This summary is based on raw feedback—no sentiment scoring applied.
Highlights the MCP's ability to fetch granular research data (data points) and let the AI synthesize it into stakeholder-ready formats. Dovetail's API returns structured records; the narrative framing comes from the AI. Useful for turning qualitative research into actionable briefs without manual copy-paste.
Use-case deep-dives
When Dovetail wins for weekly user research digests
A 5-person product team runs 8-12 customer interviews per sprint and needs to surface patterns fast. Dovetail's MCP is the right call here because the Create Data Point and Create Insight tools let you pipe raw transcripts into channels, tag themes on the fly, and generate insight summaries without leaving your AI workspace. The 18-tool scope covers the full research loop—contacts, notes, topics, insights—so you're not context-switching to the Dovetail UI for every synthesis step. The trade-off: if your team only does ad-hoc interviews (fewer than 4 per month), the overhead of maintaining channels and topics outweighs the automation win. For teams shipping user-facing features every two weeks, this MCP turns interview chaos into a searchable insight library.
When this MCP handles high-volume feedback tagging
A 12-person support org fields 200+ tickets daily and wants to spot emerging product issues before they escalate. Dovetail's MCP works because you can batch-create data points from ticket text, auto-tag topics like 'billing confusion' or 'onboarding friction', and roll up insights weekly without manual copy-paste. The Create Topic and Create Channel tools let you structure feedback by product area or customer segment, so your PM can query 'what are the top 3 onboarding blockers this month' and get an answer grounded in real tickets. The boundary: if your ticket volume is under 50 per week, a simpler tagging system (like Linear labels) is faster to set up. Above 100 tickets weekly, this MCP pays for itself in time saved and pattern-spotting speed.
When Dovetail organizes client feedback across projects
A 6-person design agency juggles 4-6 active clients and needs a single place to store critique notes, stakeholder quotes, and design rationale. Dovetail's MCP fits because the Create Note and Get Note tools let you log feedback during live critiques, link it to specific design files or prototypes, and retrieve it later when a client asks 'why did we choose this direction three months ago'. The Create Contact tool keeps stakeholder context attached to their feedback, so you're not hunting Slack threads for who said what. The catch: if your projects are one-off (no repeat clients, no long-term design systems), the upfront work of setting up channels per client isn't worth it. For agencies with retainer clients or multi-phase engagements, this MCP turns scattered critique into a queryable design memory.
Frequently asked
What does the Dovetail MCP let me do in Switchy?
It lets your team create and manage user research artifacts — channels, contacts, data points, insights, topics, and notes — directly from Switchy's chat interface. Instead of switching to Dovetail's web app to log interview findings or tag feedback, you ask the AI to do it. Useful when you're synthesizing research in Switchy and want to push structured outputs straight into your Dovetail project without context-switching.
Do I need a Dovetail admin account to connect this MCP?
No, but you need an API key with write permissions for the projects you want to manage. Dovetail's API keys are scoped to the user who generates them, so whoever connects the MCP in Switchy will determine which projects the team can access. If your Dovetail workspace restricts API access to admins or paid seats, check your plan settings before connecting.
Can the Dovetail MCP search or analyze existing research data?
No. The 18 tools are all create/delete operations — you can push new insights, contacts, and data points into Dovetail, but you can't query or retrieve existing research beyond fetching a single note by ID. If you need to search transcripts or pull aggregated insights out of Dovetail, use Dovetail's web app or their read-only API endpoints directly.
Why use this instead of just opening Dovetail in a browser tab?
Speed when you're already working in Switchy. If your team is drafting user stories or summarizing interview notes in chat, the MCP lets you create Dovetail artifacts inline without leaving the conversation. You lose Dovetail's rich editor and tagging UI, so this works best for bulk logging or scripted workflows — not for exploratory research where you need Dovetail's full interface.
Who on the team should connect the Dovetail MCP?
Whoever owns your team's Dovetail projects and has an API key. Because the MCP uses API key auth, everyone in the Switchy workspace shares the same Dovetail identity — so connect it under a service account or a lead researcher's key. If multiple people need different project access, you'll need separate Switchy workspaces or manual key rotation.