Skip to main content
Glama
thenavidm

Buffer MCP Server

by thenavidm
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Create a new post

create_post
Destructive

Create and schedule a Buffer post to a channel, adding text, media, or threads with queue, custom, or immediate timing. Requires explicit confirmation.

Instructions

Create a new post. Current Buffer GraphQL createPost. Requires explicit confirmation. Use upstream fields to bound data; provider errors are failures even with HTTP 200.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNoHow the post is being scheduled.
textNoText content of the Post. Note: for threaded posts, this needs to match the first item in the `thread` array.
dueAtNoDate when the post is scheduled to be published
assetsNoOrdered list of assets on this post.
fieldsNoUpstream field paths relative to the result, as in official CLI --fields. Default fields are bounded. Use items.id for connection nodes; pageInfo.endCursor for cursors.
ideaIdNoIs set when the Post is generated from an Idea
sourceNosource where the composer was initiated from, used for tracking.
tagIdsNoList of tag IDs
accountNoPrivate account profile name. Selects credentials only; an organization default does not restrict provider token permissions.
confirmNoMust be true for this exact user-requested Buffer mutation.
draftIdNoIs set when the Post is generated from a Draft
payloadNoComplete native input object instead of individual input fields.
metadataNo
channelIdNoChannel's Id for which we want to create the post
aiAssistedNoIf this post was created with the help of AI
saveToDraftNoIf true, saves the post as a draft instead of scheduling it. When saving as draft: - Post status will be 'draft' instead of 'buffer' - Posting limits are not checked - The post will not be published until explicitly scheduled
payload_fileNoRegular local JSON input file, no symlink, at most 1 MiB; cannot mix with payload or individual input fields.
needsApprovalNoSubmit the post for approval instead of scheduling it. A post submitted for approval is always a draft, so this conflicts with turning `saveToDraft` off. Only valid when your posting policy on the target channel requires approval.
schedulingTypeNoScheduling type to indicate notification publishing or automatic publishing

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, but the description adds two non-obvious traits: an explicit confirmation requirement and the important caveat that provider errors count as failures even on HTTP 200, which an agent cannot infer from the schema alone.

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?

Three tight sentences with the core purpose front-loaded and no filler. The 'Current Buffer GraphQL createPost' clause is slightly opaque but costs little.

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

Completeness3/5

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

For a 19-parameter, deeply nested mutation with no output schema and no annotations covering the payload/payload_file mutual exclusion, the description is thin. It covers confirmation and error semantics well but says nothing about scheduling modes, draft/approval interaction, or channel targeting beyond what the schema states.

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

Parameters3/5

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

Schema description coverage is 95% across 19 params, so the schema already documents nearly everything, including the confirm, fields, payload, and payload_file semantics. The description adds no parameter-level detail beyond the fields-bounding hint, so the baseline 3 applies.

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?

States a specific verb+resource ('Create a new post') and identifies the underlying operation ('Current Buffer GraphQL createPost'). However, it does not distinguish itself from nearby siblings like create_post_template, create_content_item_draft, or promote_content_item_draft_to_posts, leaving sibling selection to inference.

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?

'Requires explicit confirmation' signals a prerequisite, and 'Use upstream fields to bound data' hints at usage, but there is no explicit when-to-use/when-not guidance and no routing against the sibling creation tools.

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