Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Slack MCP Server send a message to #general saying hello team"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol (MCP) server that posts notifications to Slack via an
Incoming Webhook. AI agents call tools instead of shelling out to curl.
send_message — plain text and optional Block Kit blocks
send_payload — pre-built payload object or multi-part array (rate-limit aware)
send_markdown — Markdown → Block Kit conversion with Slack size limits and splitting
STDIO and SSE transports
Works with Claude Code, Cursor, OpenCode, and other MCP clients
Related MCP server: nomos-slack-mcp
git clone https://github.com/rokej/slack-mcp-server.git
cd slack-mcp-server
pip install -e ".[dev]"Or install a release wheel:
pip install https://github.com/rokej/slack-mcp-server/releases/download/v0.1.0/slack_mcp_server-0.1.0-py3-none-any.whlCopy .env.example to .env (or export the variable):
export SLACK_WEBHOOK_URL="https://hooks.slack.com/services/T…/B…/…"Create a webhook at Slack API — Your Apps → Incoming Webhooks.
# STDIO (default) — for MCP clients
slack-mcp-server
# SSE transport
slack-mcp-server --transport sse --port 8080{
"mcpServers": {
"slack-webhook": {
"command": "slack-mcp-server",
"env": {
"SLACK_WEBHOOK_URL": "${SLACK_WEBHOOK_URL}"
}
}
}
}In Agent Swarm, add Slack Webhook from
the workspace MCP catalog — Swarmer injects SLACK_WEBHOOK_URL into sandboxes.
Pin a release wheel the same way as jira-mcp-server:
ARG SLACK_MCP_VERSION=0.1.0
RUN curl -fsSL -o /tmp/slack_mcp_server-${SLACK_MCP_VERSION}-py3-none-any.whl \
"https://github.com/rokej/slack-mcp-server/releases/download/v${SLACK_MCP_VERSION}/slack_mcp_server-${SLACK_MCP_VERSION}-py3-none-any.whl" \
&& python3 -m pip install --no-cache-dir /tmp/slack_mcp_server-*.whl \
&& rm -f /tmp/slack_mcp_server-*.whl \
&& slack-mcp-server --help | head -5Tool | Purpose |
| Post plain text + optional Block Kit blocks |
| Post a pre-built JSON payload (object or array) |
| Convert Markdown to Block Kit and send |
pip install -e ".[dev]"
make test
make lintBump version in pyproject.toml and __version__ in slack_mcp_server/__init__.py
Commit, then tag and push:
git tag v0.1.0
git push origin v0.1.0The Release workflow builds slack_mcp_server-X.Y.Z-py3-none-any.whl and attaches it to the GitHub Release
Apache License 2.0 — see LICENSE.
Convert Markdown to Slack Block Kit and send via Incoming Webhook.
Handles headings, dividers, code blocks, tables (bullets when links are present), mrkdwn inline formatting, Slack size limits, and multi-part splitting with (n/m) sequence headers.
| Name | Required | Description | Default |
|---|---|---|---|
| footer | No | Optional context footer mrkdwn (appended as a context block). | |
| markdown | Yes | Markdown document to convert and send. | |
| fallback_text | No | Top-level text for push notifications. Derived from the first heading when omitted. | |
| include_default_footer | No | If true and footer is unset, append "Generated by slack-mcp-server · YYYY-MM-DD". |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description takes full responsibility for behavioral disclosure. It details specific edge-case handling: 'tables (bullets when links are present), mrkdwn inline formatting, Slack size limits, and multi-part splitting with (n/m) sequence headers.' This goes beyond a generic description and informs the agent of non-obvious transformations and constraints.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the core purpose and followed by a compact list of key behaviors. Every word earns its place, clearly conveying both the primary action and critical edge cases without unnecessary detail.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (Markdown conversion, Slack limits, multi-part splitting), the description covers essential behaviors and edge cases. An output schema exists, so return values are not required. However, it does not mention failure modes or webhook configuration prerequisites, which would make it fully complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% parameter coverage, so the baseline is 3. The description does not describe individual parameters, but the schema already provides accurate descriptions. The Markdown-related behavior (e.g., multi-part splitting) enriches the meaning of the main 'markdown' parameter, but no additional semantics are needed for the others.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: 'Convert Markdown to Slack Block Kit and send via Incoming Webhook.' It identifies the specific verb (convert/send), the resource (Markdown to Slack Block Kit), and distinguishes from siblings by focusing on Markdown preprocessing, unlike send_payload or send_message.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly states the tool's input format ('Convert Markdown') and lists supported Markdown features, making it evident when to use this tool. It does not explicitly mention exclusions or alternative tools, but the purpose is clear enough to guide selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Post a Slack message via Incoming Webhook.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | Plain-text fallback (shown in notifications / accessibility). | |
| blocks | No | Optional Slack Block Kit blocks. If omitted, posts text only. |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states the action ('Post') but does not mention side effects, response format, authentication requirements, or any error conditions. This is a significant gap for a write operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, direct sentence with zero fluff or redundancy. It is appropriately concise and front-loaded, though it sacrifices context for brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With two well-documented parameters and an output schema present, the description is minimally viable. However, it lacks usage guidance and behavioral context (e.g., when to use this over siblings, what the response contains). The complexity is low, so the missing details represent clear but not fatal gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides comprehensive descriptions for both parameters (text and blocks) with 100% coverage. The description adds no additional parameter semantics, so it does not exceed the baseline established for high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb ('Post') and resource ('Slack message'), and mentions the method ('via Incoming Webhook'). It clearly conveys the tool's primary function, but does not differentiate it from sibling tools like send_payload or send_markdown.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. With sibling tools present, the lack of any usage context or exclusions leaves the agent to guess based solely on the tool name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Post a pre-built Slack webhook payload (object or array of objects).
Same contract as send_to_slack.sh: a single payload object, or an array for multi-part messages (1s spacing between parts, 429 retry).
| Name | Required | Description | Default |
|---|---|---|---|
| payload | Yes | JSON object, array of objects, or a JSON string. |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of disclosing behavior. It covers array handling (multi-part with 1s spacing) and 429 retry, referencing a known contract. It does not mention return values, but an output schema exists. This is meaningful behavioral context beyond the schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the core action, and includes only relevant behavioral details. No fluff or redundancy, making it highly scannable for an agent.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity (one parameter, output schema present), the description provides sufficient context: input format, array behavior, spacing, and retry. It doesn't explicitly explain return behavior, but that's covered by the output schema. Sibling differentiation is slightly implicit but adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already provides 100% coverage for the payload parameter (object, array, or string). The description adds semantic value by clarifying that an array represents multi-part messages with spacing and retry, which is not evident from the schema alone. The string option isn't mentioned in the description but is covered by the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Post a pre-built Slack webhook payload') and the accepted input format (object or array). The reference to send_to_slack.sh and the sibling tool names (send_markdown, send_message) help distinguish this tool from those, as it focuses on raw payloads rather than formatted markdown or simple messages.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for raw, pre-built payloads and explicitly describes the behavior for arrays (multi-part messages). It doesn't explicitly state when to use this over siblings, but the phrase 'pre-built' and the array semantics provide clear context. A direct comparison to alternatives would make it stronger.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
The three tools are all variations of sending messages to Slack, which creates some overlap. send_payload and send_message especially could be confused, though send_markdown is clearly distinct. The descriptions help clarify input format differences, but the boundaries are not fully crisp.
All tool names follow a consistent send_verb_noun pattern: send_payload, send_markdown, send_message. This makes the set predictable and easy to navigate.
With only 3 tools, the server is tightly scoped to its purpose of sending Slack messages via webhook. Each tool covers a distinct input format, and there are no redundant or unnecessary tools.
For the stated domain of sending Slack messages via incoming webhooks, the server covers all major input formats: raw payload, markdown, and plain message. There are no obvious gaps for this narrow scope, though full Slack API features like reading messages are intentionally excluded.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MCP server connecting AI agents to 100+ apps (Gmail, Slack, Notion, GitHub) via one-click OAuth.
Hosted MCP server connecting AI assistants to 9,000+ apps and 40,000+ actions via Zapier.
MCP server for building and testing AI agents with multi-model experimentation and insights.
MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/rokej/slack-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
