Skip to main content
Glama
antonio-mello-ai

mcp-slack

by antonio-mello-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

mcp-slack

MCP server for Slack integration, built with FastMCP. Provides tools for listing channels, reading messages, and posting to Slack.

Install

pip install -e ".[dev]"

Related MCP server: slack-mcp-server

Environment Variables

Variable

Required

Description

SLACK_BOT_TOKEN

Yes

Bot User OAuth Token (xoxb-...)

SLACK_DEFAULT_CHANNEL

No

Fallback channel for slack_post_message

Copy .env.example to .env and fill in your values.

Tools

Tool

Description

slack_list_channels

List all channels accessible by the bot

slack_read_channel(channel, limit?)

Read last N messages from a channel (default: 20, max: 100)

slack_post_message(channel, text)

Send a message to a channel

The channel parameter accepts either a channel name (without #) or a Slack channel ID.

Slack App Setup

  1. Go to api.slack.com/apps and create a new app

  2. Under OAuth & Permissions, add the required Bot Token Scopes for the tools you want to use:

    Tool

    Required Bot Scopes

    slack_list_channels

    channels:read, groups:read

    slack_read_channel

    channels:history, groups:history

    slack_post_message

    chat:write

    Note: Private-channel access (groups:*) and DM scopes are only needed if the bot operates outside public channels.

  3. Install the app to your workspace

  4. Copy the Bot User OAuth Token (xoxb-...) to SLACK_BOT_TOKEN

  5. Invite the bot to channels it should access: /invite @your-bot-name

Troubleshooting: missing_scope Error

If a tool fails with a missing_scope error, it means the bot doesn't have the necessary permissions to perform that action. Check the error message to see which scope is missing, cross-reference it with the table above, and add the missing scope in your Slack App's OAuth & Permissions page. (Remember to reinstall the app to your workspace after changing scopes!)

Usage

Standalone

mcp-slack

Claude Desktop config

{
  "mcpServers": {
    "slack": {
      "command": "mcp-slack",
      "env": {
        "SLACK_BOT_TOKEN": "xoxb-your-token"
      }
    }
  }
}

Development

pip install -e ".[dev]"
ruff check src/ tests/
ruff format src/ tests/
pytest

License

MIT

Available Tools

3 tools
slack_list_channelsA

List all Slack channels accessible by the bot.

Returns a formatted list of channel names with their IDs and topics.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations, the description carries the full behavioral burden. It usefully discloses the access scope (channels the bot can see) and the shape of the result, but says nothing about pagination, result limits for large workspaces, or rate limiting. Read-only behavior is only implied by the verb "List".

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?

Two short sentences, front-loaded with the core purpose. The second sentence describing the return format is slightly redundant given an output schema exists, but it costs little and does not dilute the definition.

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 zero-parameter, read-only listing tool with a declared output schema, the description covers what is needed to invoke it. The one meaningful gap is the absence of any note about pagination or completeness of results in large workspaces.

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?

The tool takes zero parameters, which is the baseline 4 per the rubric. There is nothing for the description to clarify, and it correctly avoids inventing filtering options that the schema does not support.

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 description gives a specific verb and resource ("List all Slack channels") plus a scope qualifier ("accessible by the bot"), so the agent immediately knows what the tool returns. It does not explicitly contrast itself with siblings slack_read_channel or slack_post_message, but the verb makes the distinction obvious.

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 "use this when..." or exclusion guidance. Usage is only implied: the mention of channel names and IDs signals this is a discovery tool for resolving channel identifiers before reading or posting. An agent can infer this, but the description never states it.

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

slack_post_messageA

Send a message to a Slack channel.

Args: channel: Channel name (without #) or channel ID. text: The message text to send. Supports Slack markdown.

ParametersJSON Schema
NameRequiredDescriptionDefault
textYes
channelYes

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A3.7/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full behavioral burden. It discloses that messages support Slack markdown, but it omits important write-operation context such as required permissions, whether the bot must already be in the channel, rate limits, or error behavior.

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

Conciseness5/5

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

The description is short, front-loaded with the core action, and then structured into parameter notes. Every sentence adds relevant information without unnecessary filler.

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 simple two-parameter write tool, the description covers the basic action and parameter semantics, and the output schema means return values need not be explained. However, it remains incomplete on operational prerequisites such as authentication and channel membership, which are relevant for a Slack post operation.

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 description coverage is 0%, so the description must compensate, and it meaningfully explains both required parameters. It states that channel can be a name without '#' or a channel ID, and that text supports Slack markdown, which adds real meaning beyond the bare 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?

The description states a specific verb and resource: 'Send a message to a Slack channel.' This clearly distinguishes it from the list and read siblings, and an agent can understand the basic action without opening the schema.

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?

The purpose implies the use case, but the description gives no explicit when-to-use, when-not-to-use, or alternative guidance. It does not mention when to use slack_read_channel or slack_list_channels instead, leaving routing to the agent.

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

slack_read_channelA

Read the last N messages from a Slack channel.

Args: channel: Channel name (without #) or channel ID. limit: Number of messages to retrieve (default: 20, max: 100).

ParametersJSON Schema
NameRequiredDescriptionDefault
limitNo
channelYes

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose two real behavioral traits: a default of 20 messages and a hard cap of 100, which tells the agent about truncation. It says nothing about auth requirements, message ordering (newest-first?), or what happens beyond the 100-message ceiling.

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

Conciseness5/5

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

The purpose is front-loaded in the first sentence and the two parameter notes are one line each; there is no filler or restated boilerplate.

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?

An output schema exists, so return structure need not be described, and both parameters plus their limits are covered. What is missing is ordering/pagination behavior and access requirements, which an agent would want for a channel-read tool.

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 description coverage is 0%, so the description must compensate, and it does: it documents both parameters, including that channel accepts a name without '#' or an ID, and that limit defaults to 20 and maxes at 100. The only gap is that the type/format of channel is not further constrained.

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 (read) plus resource (Slack channel) and scope (last N messages), which is enough to separate it from slack_post_message and slack_list_channels in practice. It never explicitly names or distinguishes those siblings, so it lands at 4 rather than 5.

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

Usage Guidelines2/5

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

There is no when-to-use guidance, no statement of prerequisites (auth, bot membership in the channel), and no mention of alternatives such as slack_list_channels. The only usage information is implicit in the verb 'read'.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 3 tool updatesv0.1.1
    • First observedslack_list_channels
    • First observedslack_post_message
    • First observedslack_read_channel
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.7/5.0

Scored across 3 tools

Disambiguation5/5

Each tool maps to a distinct Slack action+resource: listing channels, reading messages, and posting messages. There is no overlap in purpose or argument shape between them.

Naming Consistency5/5

All three tools use a consistent slack_ prefix with a clear verb_noun pattern (slack_list_channels, slack_read_channel, slack_post_message). The convention is predictable throughout.

Tool Count3/5

Three tools is on the thin side for a Slack integration; the set covers only the most basic read/write loop. It is functional but leaves little room for common adjacent operations.

Completeness3/5

Core operations (list channels, read messages, post message) are present, but there are notable gaps: no thread replies, reactions, message search, user/DM lookup, or message editing. Agents can do basic workflows but will hit dead ends on common Slack tasks.

Maintenance

ActivityMaintained
ResponsivenessUnresponsive

Resources

Related MCP Connectors

Related MCP Servers