Skip to main content

Overview

MCP (Model Context Protocol) allows AI tools to connect directly to your context repository. Once connected, AI agents can retrieve, search, and update context while respecting the permissions and access controls configured in Qontext. Examples include:

Connecting via MCP

Qontext exposes a hosted MCP server:
Configure this URL in your MCP client and complete the authentication flow. Please refer to the Clients section for client-specific setup instructions.

Available operations

The MCP server exposes the context repository through a POSIX-like set of operations.

Read

Browse the file system and read content.
OperationDescription
qontext_lsList the direct children of a path (files and folders).
qontext_findRecursively list all descendants under a path. Filterable by kind (file / folder) or the date of the last update to the descendant.
qontext_catRead the full content of one or more files. If any item in the batch cannot be read, the whole call fails.
References between files are returned inline as file IDs, so a client can traverse the interconnected file system by passing a returned ID straight into qontext_cat. Locate context by content or by meaning.
OperationDescription
qontext_grepExact content search across the repository. Allows searching literally or using regex.
retrieval-toolHybrid search over the repository. Takes a qualitative, natural-language query and returns the most relevant context.

Write

Create and maintain context.
OperationDescription
qontext_writeCreate or update a file in an existing folder.
qontext_mkdirCreate a folder.
qontext_mvRename or move a file.
qontext_rmDelete a file or folder. Deletion is irreversible.
Writes flow through Qontext’s versioning: every edit is captured in the version history and reconciled into the repository, so concurrent edits are tracked rather than silently overwritten.