Fibery
Fibery is a work management platform designed to help teams collaborate, organize information, and manage their workflows.
Verdict
Common use cases
- Surface blockers from Fibery during standups
- Link customer feedback to roadmap features
- Query OKR progress without leaving chat
- Create tasks from Slack threads in seconds
- Run GraphQL reports on sprint velocity
Integration
- Vendor
- Fibery
- Category
- productivity
- Auth
- API_KEY
- Tools
- 27
- Composio slug
fibery
Tools
- Authenticate (validate token via API call)
Tool to validate existing Fibery personal API token by performing a real API call. If the call succeeds, returns the token value extracted from the Authorization header. Use the returned token in the `Authorization: Token <value>` header fo
- Authenticate with username and password
Tool to authenticate with Fibery using resource owner password credentials. Use when you need an access token by providing username and password. Include the returned token in the `Authorization: Token <access_token>` header for subsequent
- Create Entity
Tool to create a new Fibery entity. Use when you have prepared all necessary field values and need to persist a new record. Example: Create a 'Project/Task' with title and assignee.
- Delete Custom App Endpointdestructive
Tool to delete a specific custom app endpoint. Use after confirming the app and endpoint IDs to remove.
- Delete Entitydestructive
Tool to delete a specific Fibery entity by its ID. Use when you have verified the entity exists and have its GUID. Deletion is irreversible.
- Delete Filedestructive
Tool to delete a specific file. Use when you need to remove a file from Fibery by its ID.
- Exchange OAuth2 authorization code
Tool to finalize OAuth2 authentication for Fibery custom apps. Use when exchanging an authorization code for access and refresh tokens after user authorization. Notes: - In Fibery custom app flows, the access_token endpoint is typically imp
- Execute GraphQL Query
Tool to execute GraphQL queries or mutations against a Fibery space. Use when you need to fetch or modify Fibery data via the GraphQL API.
- Fetch Data from Source
Tool to fetch data from a specified source. Use after specifying the source and optional filters.
- Fetch Datalist Options
Tool to fetch options for a datalist filter field. Use after retrieving field metadata to build dynamic filters.
- Fetch Schema
Tool to fetch predefined data schema. Use after authenticating when mapping and integrating Fibery data.
- Get App Information
Tool to retrieve application information. Use when you need the version, name, description, authentication methods, and available data sources before further operations.
- Get Custom App Endpoints
Tool to list custom app endpoints. Use when you need the available custom endpoints for a given app before invoking them.
- Get Custom Apps
Tool to list all custom apps in the Fibery workspace. Use when you need the identifiers of all custom apps.
- Get Entities
Tool to query Fibery entities. Use after specifying type and fields; supports optional filters and pagination.
- Get Fibery Entity
Tool to retrieve detailed info of a specific Fibery entity by its ID. Uses Fibery Commands API (fibery.entity/query) filtered by fibery/id with q/limit = 1.
- Get File
Tool to retrieve a file by its secret or id. Prefer the file secret to download raw bytes. Returns the file content, MIME type, and original filename if available.
- Get GraphQL Schema
Tool to retrieve the GraphQL schema for the current workspace. Uses standard GraphQL introspection.
- Get User Preferences
Tool to retrieve the current user's UI preferences. Use after authentication to tailor UI to user settings.
- POST_FETCH_DATA_COUNT
Tool to return the count of records for a given Fibery type (source). Uses Fibery commands API and returns the total number of entities of the type.
- Refresh access token
Tool to refresh an access token using a refresh token. Use when the current access token has expired and a valid refresh token is available.
- Revoke Access Tokendestructive
Tool to revoke an existing Fibery API access token. Use when invalidating a user session or logging out.
- Update Entity
Tool to update an existing Fibery entity. Uses Commands API: fibery.entity/update.
- Update User Preferences
Tool to update the current user's preferences by using the Commands API. It fetches the current user id and preferences, merges the provided payload, and writes back the merged object into 'fibery/ui-preferences' of the current fibery/user.
- Upload File
Tool to upload a file to Fibery. Use when you need to attach a local file via the Fibery Files API.
- Validate Fibery account
Tool to validate account credentials. Use when confirming provided credentials (and optionally refreshing OAuth2 tokens) before further API calls.
- Validate Filter
Tool to validate filter definitions. Use when ensuring filter structure and syntax are correct before running a data query.
Setup
Setup guide
- 11. In Switchy, open your workspace settings and navigate to the Integrations tab. 2. Find Fibery in the MCP directory and click Connect. 3. Log into your Fibery workspace, go to User Settings > API, and generate a new personal API token. 4. Copy the token and paste it into the Switchy connection dialog, then click Authorize. 5. Switchy validates the token by calling Fibery's API; if successful, the integration appears as connected. 6. Open any Space in Switchy and type '@Fibery list my open tasks' to test — the MCP queries your Fibery workspace and returns results in the chat. 7. To create or update entities, @mention Fibery with the entity type and field values you want to set. 8. If authentication fails, regenerate the token in Fibery and reconnect in Switchy.
What teammates see: by default, memories from Fibery 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
List Open Tasks
@Fibery show me all open tasks assigned to me in the current sprint, grouped by priorityOpen in a Space →
Create Feature Request
@Fibery create a new feature request titled 'Dark mode for mobile app' with description 'Requested by three enterprise customers this week' and tag it as high priorityOpen in a Space →
Check OKR Progress
@Fibery what's the status of our Q2 OKRs? Show me completion percentage and any items marked as blockedOpen in a Space →
Link Feedback to Epic
@Fibery find the epic titled 'Improve onboarding flow' and link customer feedback item #4521 to itOpen in a Space →
Run Sprint Velocity Report
@Fibery run a GraphQL query to calculate total story points completed in each of the last three sprints, broken down by teamOpen in a Space →
Example outputs
Illustrative - representative of the model's voice and quality, not literal recordings.
@Fibery show me all high-priority tasks assigned to the design team that are overdue, grouped by project
Based on the current Fibery workspace, here are 8 overdue high-priority tasks for the design team: **Mobile App Redesign** (3 tasks) - Update onboarding flow mockups (due 4 days ago, assigned to Sarah) - Finalize icon set for navigation (due 2 days ago, assigned to Marcus) - Review accessibility contrast ratios (due 1 day ago, assigned to Sarah) **Website Refresh** (5 tasks) - Complete homepage hero section (due 6 days ago, assigned to Jordan) - Design pricing page variants (due 3 days ago, assigned to Marcus) - Create responsive breakpoints documentation (due 3 days ago, assigned to Jordan) - Build component library in Figma (due 2 days ago, assigned to Sarah) - Export final assets for development (due 1 day ago, assigned to Marcus) This query used the GraphQL API to filter entities by assignee team, priority level, and due date status.
This example demonstrates Fibery's flexible querying across custom entity types and relationships. The MCP requires read access to your workspace schema and entities. Response accuracy depends on how your team has structured types, fields, and relationships — Fibery's schema is fully customizable, so field names and entity types vary by workspace.
@Fibery create a new bug report titled 'Login button unresponsive on Safari 17' in the Web Platform project, set priority to Critical, and link it to the Authentication epic
Created new Bug entity in your Fibery workspace: **Title:** Login button unresponsive on Safari 17 **Project:** Web Platform **Priority:** Critical **Status:** New (default) **Created:** Just now **ID:** bug-a3f7c2d1 Successfully linked this bug to the "Authentication" epic. The bug now appears in the epic's related items list and will be tracked in the Web Platform sprint board. Team members with notifications enabled for Critical bugs in this project have been alerted automatically per your workspace rules. Note: I used your workspace's default field mappings for Bug entities. If additional required fields exist (like 'Severity' or 'Browser Version'), you may need to update them manually.
This showcases Fibery's entity creation with relationship linking across custom types. The MCP needs write permissions and must know your workspace's entity schema (type names, required fields, valid relationship targets). Side-effect: Creates a permanent record and may trigger workspace automations like notifications or status transitions. Fibery's flexible schema means field requirements vary by workspace configuration.
@Fibery analyze all feature requests created in Q1 2024, extract common themes, and draft a product roadmap summary prioritizing the top 3 themes by request volume
Analyzed 47 feature requests from Q1 2024. Here are the top 3 themes by volume: **1. Advanced Reporting & Analytics** (18 requests, 38%) Users want customizable dashboards, export to CSV/PDF, and cross-entity pivot tables. Most requests cite difficulty comparing metrics across projects without manual spreadsheet work. **2. Mobile App Improvements** (14 requests, 30%) Primary asks: offline mode for field work, faster sync, and push notifications for @mentions. Several enterprise customers noted mobile limitations block field team adoption. **3. Integration Expansion** (11 requests, 23%) Top integration requests: Salesforce (5), HubSpot (3), Jira bidirectional sync (3). Teams want to reduce duplicate data entry across tools. **Roadmap Recommendation:** Prioritize Advanced Reporting (Q2-Q3) to serve the broadest user base, followed by Mobile offline mode (Q3-Q4) to unlock enterprise expansion, then evaluate integration ROI per customer tier.
This example pairs Fibery's data retrieval with AI synthesis to surface strategic insights from your workspace. The MCP fetches raw entity data; the AI performs the thematic analysis and prioritization logic. Accuracy depends on consistent tagging and categorization of feature requests in your workspace. This read-only operation respects your existing data structure without modifications.
Use-case deep-dives
When Fibery replaces your Notion-Jira-Slack tangle
A 6-person product team juggling feature requests in Notion, engineering tickets in Jira, and customer feedback in Slack threads hits a wall when the PM spends 90 minutes a week manually syncing status. Fibery's 27 tools—especially Create Entity, Execute GraphQL Query, and the bidirectional sync capabilities—let you model the entire workflow in one graph: customer feedback links to feature specs, specs spawn Jira tickets, tickets roll up to roadmap timelines. The MCP shines here because you can script the cross-entity updates ("when this feature ships, close these 12 feedback threads") without leaving your AI workspace. The break-even point: if your team already lives in Fibery, this is a no-brainer. If you're still evaluating whether to migrate from your current stack, test the MCP with read-only queries first—Fibery's learning curve is real, and the API won't fix a bad schema design.
Pull retro insights from 40 sprints in one prompt
An engineering lead at a 12-person startup wants to answer "which types of bugs take longest to close?" across two years of sprint data. Fibery stores every task, bug report, and time estimate as structured entities with custom fields. The Execute GraphQL Query tool lets you write a single prompt—"show me median cycle time for bugs tagged 'backend' vs 'frontend' over the last 40 sprints"—and get a table back in seconds. Compare that to exporting CSVs from Jira, pivoting in Excel, and guessing at data hygiene. The catch: this only works if your Fibery schema is clean (consistent tagging, no orphaned entities). If your team's been sloppy with data entry, the MCP will surface garbage. Use this when you've already committed to Fibery as your source of truth and need ad-hoc analytics without building a BI pipeline.
Auto-link support threads to product context
A 4-person support team at a B2B SaaS company gets 30 tickets a day, half of which reference feature requests or known bugs buried in Fibery's product database. Manually searching "is this already tracked?" for every ticket burns 20 minutes per agent per day. The MCP's Execute GraphQL Query and Create Entity tools let you script a lookup: when a ticket mentions a keyword ("export broken"), the AI queries Fibery for matching bug reports or feature specs, then auto-creates a relation between the ticket and the existing entity. The agent sees the context instantly. This works best when your Fibery workspace has fewer than 10,000 entities—beyond that, query performance starts to lag without indexed views. If you're already using Fibery for product management and support lives elsewhere (Zendesk, Intercom), this MCP bridges the gap without a Zapier tax.
Frequently asked
What can Switchy do with Fibery MCP?
Switchy can read, create, update, and delete entities across your Fibery workspace — tasks, projects, documents, custom types. It queries via GraphQL and authenticates with your personal API token. The 27 tools cover entity CRUD, file management, custom app endpoints, and OAuth flows for embedded Fibery apps. You get full programmatic access to your workspace structure.
Do I need admin access to connect Fibery MCP?
No, but you need permission to generate a personal API token in your Fibery account settings. That token inherits your user permissions — if you can't edit a database or type in Fibery's UI, the MCP can't either. Admin access only matters if you're managing custom app endpoints or OAuth clients for embedded integrations.
Can Fibery MCP create custom entity types or just records?
It creates records within existing types, not the types themselves. You define your schema — databases, fields, relations — in Fibery's UI first. The MCP then uses that schema to create, query, and update entities. Schema changes (adding fields, creating new types) still happen in Fibery directly, not through the MCP.
Why use Fibery MCP instead of Fibery's API directly?
The MCP wraps Fibery's GraphQL API with natural-language intent. Instead of writing introspection queries and mutations by hand, you describe what you want — 'find all overdue tasks assigned to Sarah' — and Switchy translates that into the correct GraphQL. You skip the schema-learning curve. For custom integrations or high-volume automation, the raw API still wins.
Who on the team should connect Fibery to Switchy?
Whoever owns the Fibery workspace structure and understands which databases matter. Their API token determines what Switchy can see and modify. If multiple people need different access levels, connect separate Fibery accounts with scoped tokens. One connection per workspace is typical — the token's permissions cascade to everyone using that Switchy integration.