Can OpenCode write to my MongoDB, or only read from it?

That depends on what you allowlist. Read-style operations like Aggregate, Count Documents, and Atlas Text Search can be exposed on their own, while Bulk Write, Create Collection, and Create Index are separate tools you opt into. Expose only what the task needs.

How does the agent get data from Mongo into Confluence?

It runs the query, for example an aggregation or a facet search, then calls a Confluence operation like Create Page or Create Blog Post with the results. The two tools are wired into the same run, so the agent moves the numbers across without any glue code from you.

Where do the database credentials live?

You connect the MongoDB and Confluence credentials once, and they resolve server-side when the agent calls a tool. The connection strings and tokens never enter the model's context.

What makes OpenCode different here?

OpenCode is open and model-agnostic, so you have flexibility over the underlying model. NoClick handles running it and connecting your apps as tools.

How do I give OpenCode tools?

Connect an integration node to the agent's tools handle and choose the operations to allow. Each becomes a tool the agent can call.

Do I manage any infrastructure?

No. NoClick runs the OpenCode harness in a hosted sandbox and resolves credentials for the apps you connect.

Can it combine several apps?

Yes. Add as many integrations as you need and the agent can use them together in one run.

Connect OpenCode to Confluence and MongoDB

Connect Confluence and MongoDB to OpenCode and it can read your data and turn it into something the team can read. MongoDB is the system of record for the documents and collections you query. Confluence is where the summary, the schema note, or the health report lands. The agent runs the aggregation or the search, then writes the page, so the numbers and the write-up stay together.

Loading preview…

Opens a workflow with 83 tools ready to use.

Tools OpenCode gets

Pick the operations you want and each becomes a tool the agent can call directly while it works.

Confluence

45 tools

List Pages

List pages, optionally filtered by space, status, or title.

Get Page

Get a single page by ID, optionally including its body.

Create Page

Create a page in a space.

Update Page

Update a page. Requires the new version number (current + 1).

Delete Page

Trash (or permanently purge) a page.

List Pages in Space

List all pages within a given space.

List Child Pages

List the direct child pages of a page.

Get Page Versions

List the version history of a page.

Get Page Ancestors

Get the ancestor pages (breadcrumb path) of a page.

List Blog Posts

List blog posts, optionally filtered by space or status.

Get Blog Post

Get a single blog post by ID, optionally including its body.

Create Blog Post

Create a blog post in a space.

Update Blog Post

Update a blog post. Requires the new version number (current + 1).

Delete Blog Post

Delete a blog post.

List Spaces

List spaces, optionally filtered by key, type, or status.

Get Space

Get a single space by ID.

Create Space

Create a new Confluence space.

List Space Labels

List labels applied to a space.

List Footer Comments

List footer comments on a page.

Create Footer Comment

Add a footer comment to a page or blog post.

Update Footer Comment

Update the body of a footer comment.

Delete Footer Comment

Delete a footer comment.

List Blog Post Footer Comments

List footer comments on a blog post.

List Inline Comments

List inline (highlight) comments on a page.

Create Inline Comment

Create an inline comment anchored to selected text on a page or blog post.

Update Inline Comment

Update the body of an inline comment.

Delete Inline Comment

Delete an inline comment.

List Blog Post Inline Comments

List inline comments on a blog post.

List Attachments

List attachments on a page.

Get Attachment

Get attachment metadata, including its download link.

Upload Attachment

Upload a file as an attachment to a page (v1 multipart API).

Delete Attachment

Delete an attachment.

List Page Labels

List labels attached to a page.

Add Label

Add a label to content (page or blog post). Uses the v1 API.

Remove Label

Remove a label from content (page or blog post). Uses the v1 API.

List Content Properties

List custom content properties (key/value metadata) on a page.

Create Content Property

Set a custom content property on a page.

Update Content Property

Update an existing content property on a page (requires the property ID and current version).

Delete Content Property

Delete a content property from a page.

List Tasks

List inline tasks (checkboxes) across the site or filtered by space/page.

Get Task

Get a single inline task by ID.

Update Task

Update an inline task (e.g., mark as complete or incomplete).

Search (CQL)

Full-text / structured search via CQL (v1). Returns search results.

Search Content (CQL)

CQL search returning content objects only (v1).

Get Current User

Get the authenticated user's account info (v1).

MongoDB

38 tools

Find Documents

Find One Document

Insert One Document

Insert Many Documents

Update One Document

Update Many Documents

Replace One Document

Delete One Document

Delete Many Documents

Count Documents

Estimated Document Count

Distinct Values

Bulk Write

Find One and Update

Find One and Delete

Find One and Replace

Aggregate

List Collections

Create Collection

Drop Collection

Rename Collection

Create Index

List Indexes

Drop Index

Drop All Indexes

Vector Search

Create Vector Search Index

List Search Indexes

Update Search Index

Delete Search Index

Atlas Text Search

Create Atlas Search Index

Atlas Facet Search

List Databases

Drop Database

Run Command

Upload & Index Document

Create Multiple Indexes

What you can build

Run an aggregation over a MongoDB collection and publish the results as a Confluence page for the team.

Count documents across your MongoDB collections and post a weekly data-health summary as a Confluence blog post.

Create a new MongoDB collection and index, then document the schema decision on a Confluence page with an inline comment on the tradeoffs.

Build a MongoDB Atlas search index and record the configuration on a labeled Confluence page so the next engineer can reproduce it.

About OpenCode

OpenCode is an open, model-agnostic command-line coding agent. In NoClick it runs hosted and gains your apps as tools, so it can act on real systems rather than just edit files. Wire an integration into the agent and OpenCode can use that app’s operations directly while it works. It is a flexible choice when you want an open agent with broad model support and real tool access.

Open and model-agnostic

Flexible across many underlying models

Good general-purpose tool use

Lightweight to point at a focused task