Skip to main content
Glama
stefanoverna

Basecamp MCP Server

by stefanoverna
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Create Basecamp Document

basecamp_create_document

Create a new Basecamp document in a vault, set its title and HTML content, and publish it or save it as a draft.

Instructions

Create a new document in a vault.

HTML rules for content:

  • Allowed tags: p, span, h2, h3, h4, br, strong, em, strike, code, a (with href attribute), pre, ol, ul, li, blockquote, mark, figure, figcaption, table, tbody, tr, th, td, div, bc-attachment.

  • Wrap every paragraph in ..., and put between one paragraph and the next. Both parts are necessary: newlines and blank lines in your HTML are discarded, and Basecamp shows no space around a on its own, so two paragraphs with nothing between them are shown as one block of text. Do not rely on line breaks in your HTML to separate paragraphs.

  • Headings: use , , as appropriate.

  • Inline code: text. Preformatted blocks: text.

  • Ordered lists: .... Unordered: ....

  • Tables: Heading...Cell...

  • To mention a person: . Put the tag where the name must show in the text, for example "Thanks for the fix". The person gets a notification. If the ID is not a person, the tool returns an error and writes nothing. Get person IDs from basecamp_list_people, or from the people in other responses (assignees, creators).

  • Single image:

  • Image gallery: wrap multiple in a .

  • A bc-attachment needs an attachable_sgid. For a file that is already in Basecamp, take the sgid from the HTML content of the message, comment or card that shows it, or use basecamp_list_recordings. For a file that is not in Basecamp yet, such as an image at an external URL or a screenshot on disk, upload it with basecamp_create_attachment and use the sgid that it returns. There is no tag, so an external image URL can never be embedded directly: upload it, or accept that it stays a plain link.

  • Basecamp auto-enriches bc-attachment tags after saving (adds url, href, filename, content-type, etc.) — you never need to write those.

  • When you see an existing, already-enriched tag (e.g. from a previous list/get call), leave its inner HTML alone. Before any content_append/content_prepend/search_replace runs, it is automatically collapsed back to its minimal form (sgid, presentation, caption, and content-type for mentions) — you don't need to strip it yourself, and doing so manually is unnecessary and risks mismatched find strings.

  • Background highlights: ...

  • Text color highlights: ...

  • For both, N is 1 (yellow), 2 (amber), 3 (red), 4 (pink), 5 (purple), 6 (blue), 7 (teal), 8 (near-white), or 9 (light gray).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
titleYesDocument title
statusNoDocument status. Use "active" to publish, "drafted" to save as an unpublished draft.active
contentYesHTML document content
vault_idYesVault ID to create the document in

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv1.2.1
    • removedInput schema / properties / bucket_id
      Removed value: -{
-  "description": "Project/bucket ID",
-  "type": "number"
-}
    • changedInput schema / properties / status / description
      Previous value: -"Document status"New value: +"Document status. Use \"active\" to publish, \"drafted\" to save as an unpublished draft."
    • changedInput schema / properties / status / enum
      Previous value: -[
-  "active",
-  "draft"
-]New value: +[
+  "active",
+  "drafted"
+]
    • changedInput schema / required
      Previous value: -[
-  "bucket_id",
-  "vault_id",
-  "title",
-  "content"
-]New value: +[
+  "vault_id",
+  "title",
+  "content"
+]
  2. Addedv1.0.3

TDQS

A3.8/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (readOnlyHint=false, idempotentHint=false, destructiveHint=false), the description discloses real behavior: invalid person IDs return an error and write nothing, bc-attachment tags are auto-enriched after saving, and enriched tags are auto-collapsed before append/prepend/replace operations. It does not state what a successful call returns or what permissions are needed, keeping it out of the top tier.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded in a single sentence followed by well-organized, scannable bullets. The content rules are long but are largely load-bearing domain knowledge; only a few clauses (e.g. the reassurance about not manually stripping tags) could be trimmed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a non-idempotent create tool with no output schema, the description covers the demanding part (content HTML format), error behavior, and attachment plumbing. Minor gaps remain: it never states where vault_id comes from (basecamp_list_vaults exists) or what the call returns on success.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description substantially enriches the 'content' parameter with an exhaustive HTML contract (allowed tags, paragraph spacing, list/table syntax, bc-attachment semantics) that goes well beyond the schema's one-line 'HTML document content'. The title, status, and vault_id parameters gain no extra meaning from the description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence states a specific verb and resource ('Create a new document in a vault'), which cleanly separates it from siblings like basecamp_create_message or basecamp_create_todolist. It stops short of naming the nearest alternatives (e.g. basecamp_update_document) or clarifying it creates in an existing vault, so it is clear but not maximally differentiated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use-this-vs-another-create-tool guidance, so the agent must infer selection from the resource name. It does provide strong procedural routing for sub-tasks, naming basecamp_list_people, basecamp_list_recordings, and basecamp_create_attachment for attachable_sgid sourcing, which is useful but not tool-selection guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools