Guide
What is Fibery MCP Server?
The Fibery MCP Server connects AI assistants to your Fibery workspace via the Model Context Protocol. Once connected, your AI assistant can query databases, manage entities, run searches, and even modify your workspace schema — all through natural language.
Fibery MCP Server link → https://mcp.fibery.io/mcp
Installation
Fibery MCP server should work in any MCP Client. Here are the most popular clients:
Claude (Desktop/Web)
Navigate to Settings → Connectors → Add custom connector (available for paid plans)
Fill in the connector details and submit:
After adding the connector, Claude will automatically initiate the OAuth 2.0 authentication process (no API tokens needed). If no luck, click Connect button for Fibery tool and try again.
ChatGPT
Navigate to Settings → Connectors → Advanced Settings
Enable "Developer mode" to allow MCP servers with any set of tools
Navigate back to Settings → Connectors and hit "Create" in the top right corner
Fill in the connector details and submit:
After adding the connector, OpenAI will automatically initiate the OAuth 2.0 authentication process (no API tokens needed). If no luck, click Connect button for Fibery tool and try again.
For other tools check Fibery MCP Server Installation
What the Fibery MCP Server can do
Here's the content reformatted as lists:
Read operations
Explore workspace structure — Discover spaces, databases, and fields
Query databases — Filter, sort, and paginate any database
Full-text search — Search across all content in the workspace
Activity history — See who changed what, and when
Retrieve view data — Pull data from saved views as configured
Write operations
Manage entities — Create, update, and delete entities
Workflow management — Move entities through workflow states
Assignments and links — Assign users and link related records
Rich-text documents — Read and write entity descriptions and documents
File attachments — Attach files to records by fetching from a URL
Schema modifications
Spaces and databases — Create and delete spaces and databases
Fields — Add fields of any type: text, number, date, dropdown, relation, formula
Workflow stages — Configure workflow states
Views — Create and update boards, timelines, calendars, and forms
For a full list of available tools, check the full tools reference →Fibery MCP Server Tools References
Example prompts
These examples show the kinds of requests your AI assistant can handle once connected:
Querying and reporting
"Show me all urgent bugs that aren't done yet."
"What did team X work on this week?"
"Who has the most open bugs assigned to them right now?"
"Which Icebox features have the highest customer demand?"
"Give me a sprint health report — what's at risk and what's overdue?"
"Write this week's release notes from everything that shipped."
Entity detail and context
"Give me a full picture of feature X — state, owner, linked bugs, description."
"Prepare my standup — what did I work on yesterday and what's stuck?"
"Find all bugs that have been In Progress for more than a week with no updates."
Creating and updating
"Create a bug: form fields lose their value when switching tabs. Assign it to Nastya and mark it urgent."
"Move all Implemented features to Done."
"Link this customer request to the Figma plugin feature."
"Triage new customer requests — match each one to the most relevant feature."
Schema changes
"Add a Severity field to bugs — Critical, High, Medium, Low."
"Set up a new Design space with task tracking linked to features."
FAQ
Querying data with Fibery MCP is slow. How to improve quality/speed of answers?
Make use of skills - in a single session, get LLM to do what you wanted with Fibery MCP. In the end, ask it to pack it into a reusable document/skill so that it can re-used later.
Give as much information as you can - what databases to use, what fields to query, with what filters. All of that will help LLM to really focus.
Lastly, you may copy contents of our Entity API guide as markdown and ask LLM to find examples of how fibery queries are constructed. It will NOT work with all tools, but in case of query, it will, because the input structure of the tool is very close to raw API call.
I see a "Custom MCP server introduces risk" warning
This is a generic warning shown for all MCP servers by the AI client — it does not indicate a vulnerability in the Fibery MCP Server. The Fibery MCP Server follows the same security model as other Fibery integration endpoints.
I see "This MCP server cannot be used in Deep Research/Agent"
This is expected. Fibery's MCP Server does not implement the search and fetch tools that Deep Research and Agent modes require, because they are not relevant to typical Fibery use cases.
Fibery's MCP Server works well for:
Data querying and reporting
Entity creation and updates
Workspace automation and integrations
I see the error "no transport found for session id"
This error means the client cannot find an active session connection. Try these steps in order:
Re-add the connector. Delete the Fibery MCP entry from your client's connector list and add it again. This clears any stale session cache.
Check the client version. Make sure your AI client is up to date and compatible with the MCP server.
Restart the client. A WebSocket session may fail to initialize on first connect. Restarting often resolves it.
If none of these steps help, the issue may be server-side. Contact Fibery support with your session details.