Fibery MCP

Live

API KEY

PROJECT MANAGEMENT

Project Management

Connect your AI agent to Fibery so it queries, creates, and updates entities across the user's interconnected workspace — all with per-user credentials.

  • Acts as the user. Every entity created or updated is attributed to the Fibery user who authorized the agent, not a shared service account.
  • Credentials stay vaulted. AES-256, resolved at request time, never exposed in LLM context.
  • Scoped before every call. Permissions enforced per-user. 90-day audit trail on every tool invocation.
Fibery MCP
agent · Acme Q3
Run
What tasks are overdue in the product backlog right now?
S
fibery_entities_query
85ms
Fibery agent
Found 7 overdue tasks in Product Backlog — 3 assigned to you, 4 unassigned. Oldest is 12 days past due.
Sources: 7 entities, Product Backlog space
fiberymcp
7 entities
18:29
Message Claude...

Tools your project management agent reaches for on Fibery MCP, scoped per user.

CALL ANY TOOL
Each tool maps to a core Fibery operation — querying relational entities, creating records, updating fields, and managing documents — all resolved under the authorizing user's token.
fiberymcp_add_chart_tab
Add chart tab
Appends a new chart tab to an existing Fibery report. **Prerequisite:** You need a `reportId` from `create_report` or `get_reports_list`. Call `display_report_schema` first to discover valid field expressions for the report's sources. Reports are a specialized domain: call `get_fibery_skill` with `skill: "reports"` for the full report model, expression syntax, palettes, conditions, and workflow.
Parameters
Name
Type
Required
Description
reportId
string
Required
UUID of the report to add the chart tab to (from create_report or get_reports_list).
x
array
Required
X-axis dimensions. Put categorical/date dimensions before numeric.
y
array
Required
Y-axis dimensions. Put categorical/date dimensions before numeric.
color
object
Optional
Color-coding (legend) dimension. Only one allowed.
description
string
Optional
Tab description.
dimensionConditions
array
Optional
Dimension-level filters (must reference expressions already used in the tab).
fieldConditions
array
Optional
Field-level filters applied to this tab's data.
label
array
Optional
Label dimensions shown on chart points/bars.
palette
string
Optional
Color palette. See get_fibery_skill(skill:'reports') for palette selection guidance.
size
object
Optional
Size-coding dimension. Only one allowed.
title
string
Optional
Tab title.
type
string
Optional
Chart type. Defaults to 'scatterplot' if omitted. See get_fibery_skill(skill:'reports') for chart-type guidance.
fiberymcp_add_file_from_url
Add file from url
fiberymcp_append_document_content
Append document content
fiberymcp_create_avatars_fields
Create avatars fields
fiberymcp_create_custom_app_dev_token
Create custom app dev token
fiberymcp_create_files_fields
Create files fields
fiberymcp_create_primitive_fields
Create primitive fields
fiberymcp_create_single_select_fields
Create single select fields
fiberymcp_delete_avatars_fields
Delete avatars fields
fiberymcp_delete_databases
Delete databases
fiberymcp_delete_fields
Delete fields
fiberymcp_delete_space
Delete space
fiberymcp_display_report_schema
Display report schema
fiberymcp_fetch_by_url
Fetch by url
fiberymcp_get_connectors_list
List get connectors
fiberymcp_get_documents_content
Get documents content
fiberymcp_get_entity_mention
Get entity mention
fiberymcp_get_manual_import_link
Get manual import link
fiberymcp_get_report
Get report
fiberymcp_insert_document_blocks
Insert document blocks
fiberymcp_query
Query
fiberymcp_read_document
Read document
fiberymcp_remove_collection_items
Remove collection items
fiberymcp_rename_databases
Rename databases
fiberymcp_reply_document_comment
Reply document comment
fiberymcp_search
Search
fiberymcp_set_block_attrs
Set block attrs
fiberymcp_update_dimension
Update dimension
fiberymcp_update_multi_select_fields
Update multi select fields
fiberymcp_update_tab
Update tab

For more tools, view docs.

Build your Agent
The same per-user token pattern works across LangChain, OpenAI, Anthropic, and Google ADK — no auth code changes per framework.
Python · LlamaIndex
Try these prompts
Paste any prompt into your agent to get started with Fibery.
Status and triage
Copy the prompt
Copied
What tasks in the product backlog are overdue and unassigned?
Copy the prompt
Copied
Show me everything assigned to me that's due this week.
Copy the prompt
Copied
Which bugs in the current sprint haven't been updated in 3 days?
Copy the prompt
Copied
List all open tasks across spaces where priority is high.
Create and update
Copy the prompt
Copied
Create a new feature request in the Product space titled '[title]' with description '[desc]'.
Copy the prompt
Copied
Mark the task '[task name]' as done and add a comment summarizing what was completed.
Copy the prompt
Copied
Update the priority of all unassigned bugs in the current sprint to High.
Search and summarize
Copy the prompt
Copied
Summarize all meeting notes created this week across the team's spaces.
Copy the prompt
Copied
Find everything related to the '[project name]' initiative and give me a status summary.
Copy the prompt
Copied
List all entities linked to the goal '[goal name]' and show their current status.
SEE HOW AUTH WORKS
The user authorizes once via API key. Every subsequent agent call resolves their token from the vault and enforces scope before the tool executes.
1
Authorize
Your user connects
Fibery MCP
once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access
Who:
user ‘A’
when:
Once per user
access:
Limited to user
2
Store
Their
Fibery MCP
token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection
vault:
encrypted
scope:
per-user
tokens:
auto-refreshed
3
Resolve
When your agent calls a
Fibery MCP
tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs
speed:
~40ms
check:
before every call
seen by:
nobody
4
Audit
Every
Fibery MCP
tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it
history:
90 days
export:
SIEM-ready
logged:
every call
Test other agents
See the same per-user auth pattern applied to Notion, Asana, Jira, and 100+ other connectors.
Engineering Teams
Engineering standup agent
Pulls commits from GitHub and GitLab, tracks issue movement in Jira, and posts a per-engineer standup brief to Slack. Each engineer's activity is read on their own delegated OAuth.
Engineering Teams
DevOps assistant agent
Polls GitHub for failing checks and stale PRs, opens Linear issues for the ones that need work, and posts a daily digest to Slack. It acts as the engineer, not a shared service account.
Engineering Teams
Slack triage
Polls Slack for new messages, classifies bugs and support requests with a LangGraph router, files GitHub issues or Zendesk tickets, and confirms in the thread.
People Ops and HR teams
Performance review collector
Collects review feedback from Airtable and Google Forms scoped to each manager's direct reports, writes per-employee summaries to Notion, and DMs the manager a Slack digest.
Test other agents
See the same per-user auth pattern applied to Notion, Asana, Jira, and 100+ other connectors.
ENGINEERING
Engineering standup agent
Pull commits from GitHub and GitLab, track Jira issue movement, and post a per-engineer standup brief to Slack.
ENGINEERING
DevOps assistant agent
Poll GitHub for failing checks and stale pull requests, open Linear issues for the ones that need work, and digest to Slack.
ENGINEERING
Slack triage agent
Classify new Slack messages as bugs or support requests, file the GitHub issue or Zendesk ticket, and reply in the thread.
PEOPLE OPS
Performance review collector agent
Collect review feedback from Airtable and Google Forms per manager, summarise each report in Notion, and DM the digest in Slack.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
01.
Shared tokens break per-user analytics
A shared API key looks fine in a demo. In production every Fibery write looks like a service account. You lose attribution, audit trails become useless, and compliance reviews fail. Scalekit resolves the real user credential on every call.
// shared token
fibery_entity_create → bot_service_account
audit: who updated this? unknown

// scalekit
fibery_entity_create → user_alice ✓
audit: alice@acme.com, 14:32 UTC
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
Fibery MCP today. Others tomorrow.
“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”
Venu Madhav Kattagoni
Head of Engineering / Von
FAQs
Frequently Asked Questions
Does each user need their own Fibery API key, or can I share one key across all users?
Each user needs their own API key. Scalekit stores a separate credential per user in an AES-256 vault and resolves the right key at request time. Sharing a single key collapses per-user attribution and breaks audit trails — every Fibery action appears as a single service account regardless of who triggered it.
How are API keys stored and protected?
Keys are encrypted at rest using AES-256 and stored in Scalekit's vault, namespaced per tenant. They are never written to logs, never passed through LLM context, and never exposed in tool call parameters. Keys are decrypted only at the moment the tool executes and passed directly to the Fibery API.
Can I restrict which Fibery tools a given user or agent is allowed to call?
Yes. Scalekit's listScopedTools API returns only the tools permitted for the authenticated user in the current session. You can configure scope at the connector level, the user level, or the tenant level. Tools outside the granted scope return a 403 before the Fibery API is ever contacted.
What happens when a user revokes their Fibery API key or their account is deactivated?
The next tool call that attempts to resolve that user's credential will fail with an auth error. Scalekit surfaces this as a structured error your agent can handle — typically by prompting the user to re-authorize. No other user's credentials are affected, and the revoked key is purged from the vault.
Fibery organizes data as interconnected spaces and types. Does the connector handle relational queries across multiple entity types?
Yes. The fibery_entities_query tool accepts a filter object that can traverse Fibery's relational graph — for example, querying Tasks linked to a specific Goal or Feature. Scalekit passes the filter through to the Fibery API under the authorizing user's token, so relation traversal respects that user's workspace permissions.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""fiberymcp"": {
""url"": ""https://mcp.scalekit.com/fiberymcp"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.fiberymcp]
url = ""https://mcp.scalekit.com/fiberymcp""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""fiberymcp"": {
""url"": ""https://mcp.scalekit.com/fiberymcp"",
""type"": ""http""
}
}
}