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
Query rich text content — get content of rich text fields including linked entities and inserted images and files. Supported files formats: PNG, JPEG, GIF, WebP, PDF, CSV, Markdown, Plain Text (up to 20 MB each).
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 tables, boards, timelines, calendars, forms, and reports
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."
Next steps
Check Fibery MCP Server FAQ