# Fibery MCP connector

Connect Fibery to Elaichi and Claude, ChatGPT, Cursor or any MCP client can search your spaces, read and update features, bugs and documents, and change states, all as you, with every call logged.

Source: https://elaichi.ai/connectors/fibery/

## Facts

| | |
| --- | --- |
| Application | Fibery |
| Category | Product Development |
| AI tools | 50 |
| Authentication | Connects over OAuth |
| Bring your own OAuth app | No |
| Native MCP | Yes. Fibery builds and runs this MCP server. Elaichi adds sign-in, access controls and an audit log on top |
| Support for its tools | the.fibery.io/@public/User_Guide/Guide/Contact-Support |
| MCP endpoint | https://api.elaichi.ai/mcp |
| Works with | Claude, ChatGPT, Cursor, any MCP client, and the Elaichi Agent |
| Tools advertised by name | No. Connected tools are never listed one by one, however few there are. The endpoint advertises `search_tools` and `execute_tool` instead |

## What you can ask once Fibery is connected

- Summarize bugs moved to Done in the Platform space this week
- Create a feature in the Roadmap database from these customer notes
- Which initiatives in the Q3 view have no owner yet?

## Connect Fibery in Elaichi

This happens once for the organization, before any client is involved.

1. Open Connections, choose Add connection, and pick Fibery.
2. Optionally set Share with, then press Connect.
3. Approve it in Fibery. Fibery's own window opens. Whoever approves it decides what this connection can reach.

Credentials are vaulted and nobody, including the AI, reads them back. The connection becomes a toolbox immediately, so you can curate which Fibery tools are exposed, rename them, or freeze arguments before anyone points a client at it.

## Fibery MCP connector for Claude

Endpoint: https://api.elaichi.ai/mcp

1. Open Customize, then Connectors.
2. Press Add.
3. Name it, paste the MCP server URL, then Continue.
4. Sign in and approve.

On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.

## Fibery MCP connector for ChatGPT

Endpoint: https://api.elaichi.ai/mcp

1. Open Plugins, then press the + button.
2. Name it and paste the endpoint into Server URL.
3. Leave Authentication on OAuth, then tick the risk acknowledgement.
4. Press Create, then sign in and approve.

Works on the web today. The plugin directory lives at chatgpt.com/plugins.

## Fibery MCP connector for Cursor

Endpoint: https://api.elaichi.ai/mcp

1. Open `~/.cursor/mcp.json`.
2. Add the endpoint under `mcpServers`.
3. Reload Cursor, then sign in and approve.

Set up per machine, so repeat it on each computer you work from.

## Connect Fibery to any MCP client

Endpoint: https://api.elaichi.ai/mcp

1. Add the endpoint as a remote MCP server.
2. Sign in and approve.

The Elaichi Agent already has these tools, with nothing to set up.

## What the consent screen decides

Only Read is granted by default, which is not enough to call a Fibery tool. Over MCP there is no trusted place to confirm a write in the moment, so the consent screen is the standing approval rather than a formality. Grant Read and Run tools. Think hard before granting Delete, which reaches into connected apps and cannot be undone.

## What teams do with Fibery through Elaichi

### Catch the roadmap up after a customer call

Product. Tell the agent what the customer asked for and it creates or updates the feature in Fibery, links it to the account, and sets the right state.

### Move bugs through states from the terminal

Engineering. From Cursor, ask which bugs are assigned to you, set one to In Progress, and append a note to the bug's document without leaving your editor.

### Keep specs current in Fibery documents

Design. Paste decisions from a review and the agent appends them to the spec document in Fibery, so the written spec matches what was agreed.

### Turn feedback into linked Fibery requests

Customer Success. Drop in a support thread and the agent creates a feedback entity, adds it to the right feature's collection, and reports what is already planned.

### Summarize interview notes into insights

Research. Ask for the themes across this month's interview documents in Fibery and get a summary with each insight linked back to the entities it came from.

### Ask how the quarter's initiatives are tracking

Leadership. Query the initiatives view in Fibery in plain language and get a status rundown, with the entities that have no owner or have stalled called out.

## Elaichi vs Zapier MCP vs Composio for Fibery

All three can connect Fibery to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.

| What to check | Elaichi | Zapier MCP | Composio |
| --- | --- | --- | --- |
| Where the AI connects | One address for the whole organization. Endpoint: https://api.elaichi.ai/mcp | A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over Fibery tools | Allow or restrict single Fibery tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per Fibery call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | $15 per user per month. | 2 tasks per successful call. | Billed per tool call. |

Sources: Zapier MCP [docs](https://docs.zapier.com/mcp/get-started/quickstart), [security](https://docs.zapier.com/mcp/manage/security), [usage](https://docs.zapier.com/mcp/features/usage); Composio [docs](https://docs.composio.dev/docs/composio-connect), [gateway](https://composio.dev/mcp-gateway), [enterprise](https://composio.dev/enterprise), [pricing](https://composio.dev/pricing). Checked September 2026.

Longer take: [Zapier MCP alternative](/blog/zapier-mcp-alternative/) and [when you don't need an MCP gateway](/blog/when-you-dont-need-an-mcp-gateway/).

## Frequently asked questions

### How do I connect Fibery to Claude?

In Elaichi, choose Fibery and sign in to your Fibery workspace over OAuth, the same way you sign in to Fibery normally; there is no client ID or secret to generate. Then in Claude open Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Claude will ask you to sign in to Elaichi, and Fibery is available in the conversation from then on.

### Does Fibery work with ChatGPT and Cursor as well as Claude?

Yes. Once Fibery is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any MCP client and the Elaichi Agent. You connect Fibery once and every client picks it up.

### What can an AI agent actually do with my Fibery data?

An agent can search and query entities across your Fibery spaces, read the data behind a view, open and edit documents, create or update features, bugs and other entities, set their states, and link them together. It can also create or rename databases and spaces if your role allows. Short, concrete asks such as "set this bug to Done" work better than long paragraphs.

### Does connecting Fibery give the AI every space in my workspace?

No. The agent works inside the Fibery access of the person who signed in, so it sees only the spaces, databases and entities that person can already see. Elaichi can narrow that further with roles and restrictions, and it can never widen it beyond what Fibery itself grants.

### Can my team share one Fibery connection?

Yes. One person connects Fibery in Elaichi and shares it with a team, and nobody else ever handles a Fibery credential. Each teammate still signs in to Elaichi as themselves, so the audit log names the actual person behind every change in Fibery.

### Can I stop an agent from deleting or changing things in Fibery?

Yes. Restrictions in Elaichi work per action, so you can allow searching and reading in Fibery while blocking deleting entities, removing databases or deleting spaces. A restricted action is never advertised to Claude, ChatGPT or Cursor, so no prompt can reach it.

### What happens to a Fibery connection when someone leaves?

Offboarding a person in Elaichi ends their access to Fibery through every client at once. A Fibery connection they shared keeps working for everyone else on the team. If you want Fibery gone entirely, disconnecting it once in Elaichi removes it from Claude, ChatGPT, Cursor and every other client.

### Does the Fibery MCP connector work with Gemini, Codex, Claude Code or other MCP clients?

Yes. Fibery is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.

### Is Elaichi an alternative to Zapier MCP for Fibery?

Yes. Both let Claude, ChatGPT or Cursor use Fibery. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Fibery call.

### How is Elaichi different from Composio for Fibery?

Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Fibery: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.

## All 50 Fibery tools

Every tool below is callable through https://api.elaichi.ai/mcp once Fibery is connected, subject to the toolbox it is in and the restrictions on the caller.

- **Schema** (Action). Returns the high-level structure of the workspace: all spaces and their databases, without field details.
- **Schema detailed** (Action). Returns field definitions and enum values for specific databases in YAML format.
- **Get me** (Get). Returns information about the currently authenticated user.
- **Query** (Search). Executes a Fibery Query API command against any database. Supports field selection, filtering, sorting, pagination, sub-queries, and aggregation.
- **Search** (Search). Searches workspace content using BM-25 keyword matching against entity titles, descriptions, document content, and comments.
- **Search guide** (Search). Retrieves information from the Fibery User Guide via keyword search.
- **Search history** (Search). Searches the workspace activity history for entity and schema changes.
- **Query views** (Search). Returns saved views (boards, grids, timelines, documents, etc.) matching optional filters.
- **Fetch view data** (Action). Executes a view's configured query and returns the entities it would display, with the view's own filters, fields, and sort order applied.
- **Create entities** (Create). Creates one or more entities in a database.
- **Update entities** (Update). Updates specified fields on existing entities. Only provided fields are changed; all other fields are left untouched.
- **Delete entities** (Delete). Permanently deletes entities by their UUIDs. This action cannot be undone.
- **Set state** (Set). Sets the workflow/state of a single entity.
- **Get entity links** (Get). Generates Fibery web links for entities by their public IDs.
- **Get documents content** (Get). Returns the Markdown content of one or more entity documents by their secrets.
- **Set document content** (Set). Replaces the full content of a Collaboration~Documents/Document field on an entity.
- **Append document content** (Action). Appends Markdown content to the end of an existing document field. Does not replace existing content.
- **Add collection items** (Add). Adds items to an entity's collection field (e.g., assignees, tags, linked bugs).
- **Remove collection items** (Delete). Removes items from an entity's collection field.
- **Create space** (Create). Creates a new space in the workspace.
- **Delete space** (Delete). Deletes a space and all its databases. Restorable via Activity Log.
- **Create databases** (Create). Creates one or more databases within existing spaces.
- **Rename databases** (Action). Renames one or more databases. Changing the space prefix moves the database to a different space.
- **Delete databases** (Delete). Deletes one or more databases. Restorable via Activity Log.
- **Create primitive fields** (Create). Creates one or more primitive (scalar) fields in databases.
- **Rename fields** (Action). Renames one or more fields.
- **Delete fields** (Delete). Deletes one or more fields. Restorable via Activity Log.
- **Create relation fields** (Create). Creates a relation between two databases. One relation definition creates a field in both databases.
- **Create single select fields** (Create). Creates one or more single-select fields with predefined options.
- **Update single select fields** (Update). Updates options of existing single-select fields.
- **Create multi select fields** (Create). Creates one or more multi-select fields. Same parameters as create_single_select_fields, without defaultOption.
- **Update multi select fields** (Update). Updates options of existing multi-select fields. Same parameters as update_single_select_fields, without defaultOption.
- **Create workflow field** (Create). Creates a workflow (state) field for tracking entities through lifecycle stages.
- **Update workflow field** (Update). Updates the states of an existing workflow field.
- **Delete workflow field** (Delete). Deletes the workflow field from a database. Restorable via Activity Log.
- **Create formula field** (Create). Creates a calculated formula field. The formula expression is generated automatically from a natural-language description.
- **Update formula field** (Update). Updates an existing formula field by regenerating its expression. The new formula must produce a compatible type with the existing field.
- **Create files fields** (Create). Creates file attachment fields.
- **Create avatars fields** (Create). Enables avatar/profile picture attachments on entities. Creates an "avatar/avatars" field automatically.
- **Delete avatars fields** (Delete). Removes the "avatar/avatars" field. Restorable via Activity Log.
- **Create comments fields** (Create). Enables comments on entities. Creates a "comments/comments" field automatically.
- **Delete comments fields** (Delete). Removes the "comments/comments" field. Restorable via Activity Log.
- **Create icon fields** (Create). Enables emoji icons on entities. Creates an "icon/icon" field automatically.
- **Delete icon fields** (Delete). Removes the "icon/icon" field. Restorable via Activity Log.
- **Create view** (Create). Creates a new view in the workspace.
- **Update view** (Update). Updates an existing view. Only provided fields are changed.
- **Delete views** (Delete). Deletes views by UUID. Entity data is not affected. Restorable via Activity Log.
- **Add file from URL** (Add). Downloads a file from a URL and attaches it to an entity's file field.
- **Get connectors list** (Get). Returns all available built-in connectors (import integrations) in the workspace.
- **Get import link** (Get). Generates a URL to the Fibery import wizard for a given connector and target.