Tool reference

The Within MCP exposes workspace data tools that an AI assistant can chain to answer questions grounded in a customer’s workspace. It also provides an optional feedback submission tool. The point of this reference is not to enumerate APIs — it’s to help you pick the right tool for the goal at hand.

How the toolset is organized

Every workflow reduces to: find the right process(es) → fetch detail → gather evidence → traverse relationships → synthesize.

Group	What it covers	When to start here
Standard entry points	`search`, `fetch`	The default starting path for any process question
Process Index	Process browsing and relationships	Explore a business area or investigate a process in more detail
Process observations	Changes, captured work, and participation	Understand what happened and find supporting evidence
Artifacts	Document search, content retrieval, in-document text search	The user names a document or recording
Workspace and directory	Workspaces and people	Confirm your workspace or find a contributor
Feedback	Submit explicitly approved user feedback	Sending feedback about the integration to Within

Each group has a purpose-based tool directory and a Current schema section for input details.

Shared parameters

These parameters apply to every tool and are included in each raw JSON Schema.

Parameter	Type	Required	Description
`context`	string	Yes	Purpose of the request.
`mcp_thread_id`	string or null	No	Identifier linking related requests. Default: `null`.

Before you call

Read Operating principles — the conventions for staying grounded, iterating on search, separating observed from inferred, and avoiding common mis-uses (treating search_* snippets as final answers, exposing internal IDs in user-facing prose).

What the assistant should do with results

A human using the Advisor might use two or three tools per question. An assistant in an agentic loop can chain ten or more — searching, drilling in, cross-referencing, synthesizing. The whole point of the MCP is that composition is the value. See How-to guides for end-to-end recipes.

Overview

Tools by purpose

How the toolset is organized

Shared parameters

Before you call

What the assistant should do with results

​How the toolset is organized

​Shared parameters

​Before you call

​What the assistant should do with results

How the toolset is organized

Shared parameters

Before you call

What the assistant should do with results