Skip to main content
Glama
smallest-inc

Smallest MCP Server

Official
by smallest-inc
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Remote

publish_draft

Commit pending draft edits on a branch as a new revision, serving immediately if live. Waits for security check and reports outcome; can discard draft instead.

Instructions

Publish a branch's pending draft edits, committing them as a new revision. If the branch is live, the changes serve immediately; otherwise use make_branch_live to serve them. Publishing runs an async security check on the prompt; this tool waits for it and reports the real outcome — if the check is still running after ~60s the changes aren't committed yet (they commit automatically once it passes), and if it fails the draft stays open so you can fix the prompt and publish again. Can also discard the pending draft instead of publishing.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
labelNoRevision label (max 200 chars, e.g. 'Changed voice to yuvika')
actionNoWhether to publish the draft (commit it) or discard itpublish
agent_idYesThe agent ID
branch_idNoBranch to publish (from list_branches). Omit to use the live branch; if the agent has multiple branches you'll be asked to pick one.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed7 schema fields changedv0.11.1
    • changedInput schema / properties / action / description
      Previous value: -"Whether to publish the draft (make it live) or discard it"New value: +"Whether to publish the draft (commit it) or discard it"
    • removedInput schema / properties / activate
      Removed value: -{
-  "default": true,
-  "description": "Activate the published version once its security check passes (default true). Pass false to publish only — activate later with activate_version.",
-  "type": "boolean"
-}
    • addedInput schema / properties / branch_id
      Added value: +{
+  "description": "Branch to publish (from list_branches). Omit to use the live branch; if the agent has multiple branches you'll be asked to pick one.",
+  "type": "string"
+}
    • removedInput schema / properties / description
      Removed value: -{
-  "description": "Changelog description (max 2000 chars)",
-  "type": "string"
-}
    • removedInput schema / properties / draft_id
      Removed value: -{
-  "description": "The draft ID to publish (returned by update_agent_config, update_agent_prompt, add_agent_tool, set_pre_call_api, etc.)",
-  "type": "string"
-}
    • changedInput schema / properties / label / description
      Previous value: -"Version label (max 200 chars, e.g. 'Changed voice to yuvika')"New value: +"Revision label (max 200 chars, e.g. 'Changed voice to yuvika')"
    • changedInput schema / required
      Previous value: -[
-  "agent_id",
-  "draft_id"
-]New value: +[
+  "agent_id"
+]
  2. Changed2 schema fields changedv0.8.1
    • addedInput schema / properties / activate
      Added value: +{
+  "default": true,
+  "description": "Activate the published version once its security check passes (default true). Pass false to publish only — activate later with activate_version.",
+  "type": "boolean"
+}
    • changedInput schema / properties / draft_id / description
      Previous value: -"The draft ID to publish (returned by update_agent_config or update_agent_prompt)"New value: +"The draft ID to publish (returned by update_agent_config, update_agent_prompt, add_agent_tool, set_pre_call_api, etc.)"
  3. First observedv0.1.1

TDQS

A4.8/5.0
Behavior5/5

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

No annotations provided, but description fully discloses async security check, ~60s wait, outcome reporting, conditional commit, and failure handling. No contradictions.

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?

Single paragraph, front-loaded with main action. Every sentence adds value, though slightly long. No redundancy.

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

Completeness5/5

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

Covers all key aspects: main operation, branch live state, async check behavior, discard alternative. No output schema needed, but description is thorough for selection and invocation.

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% with descriptions. The description adds context for branch_id (omit for live) and action (discard vs publish), slightly enhancing the schema.

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

Purpose5/5

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

Starts with explicit verb and resource: 'Publish a branch's pending draft edits, committing them as a new revision.' Clearly distinguishes from siblings like make_branch_live and delete_branch by describing the relationship and alternative actions.

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

Usage Guidelines5/5

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

Explicitly states when to use (to publish draft) and when not (if branch not live, use make_branch_live). Also covers discard option and async behavior with timeouts and retry guidance.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/smallest-inc/mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server