A read-only MCP server that gives AI coding agents access to CometChat's documentation, enabling them to research and write real-time chat, voice, video, and moderation integrations from natural-language prompts. No account, API key, or authentication is required.
Tools:
search_cometchat_docs: Search across SDK guides (JavaScript, React, iOS, Android, Flutter, React Native), UI Kit references, REST API docs, integration tutorials, and OpenAPI specs. Returns ranked snippets with titles and direct links. Supports an optional version filter (e.g. v4, v3).
fetch_cometchat_doc_page: Retrieve the full markdown content of any CometChat documentation page by providing a full URL or relative path.
get_cometchat_implementation_bundle: Retrieve a curated, ready-to-run implementation bundle for a specific integration scenario, including prerequisites, install commands, configuration steps, working code examples, and common pitfalls. Available bundles cover:
React UI Kit quickstart
React Native UI Kit quickstart
Flutter UI Kit quickstart
iOS UI Kit (SwiftUI) quickstart
Android UI Kit (Jetpack Compose) quickstart
Vanilla JS SDK messaging basics
No-code widget embed (HTML, Webflow, Wix, WordPress, Shopify, Squarespace)
Moderation setup (AI rules, image moderation, webhooks)
Multi-tenant SaaS chat (tenant isolation, Auth Tokens)
Presence indicators, typing indicators, and read receipts
Compatible with Claude, Cursor, Windsurf, VS Code Copilot, Codex, and any MCP-compatible agent.
Enables integration with Android apps using the CometChat Android UI Kit (Jetpack Compose) and SDK for real-time chat, voice, and video.
Provides Angular UI Kit integration for adding chat, voice, and video capabilities to Angular applications.
Allows Flutter apps to integrate real-time chat, voice, and video using the CometChat Flutter UI Kit and SDK.
Enables iOS apps to integrate real-time chat, voice, and video using the CometChat iOS UI Kit (SwiftUI) and SDK.
Provides the JavaScript SDK for integrating real-time messaging and media into web applications.
Supports Android app integration using the Jetpack Compose-based CometChat UI Kit for modern Android development.
Facilitates integration with Next.js applications, leveraging React UI Kit for building chat features.
Allows React applications to add real-time chat, voice, and video using the CometChat React UI Kit.
Provides a no-code widget integration for Shopify stores to add chat functionality.
Offers a no-code widget for embedding chat into Squarespace websites.
Enables Swift-based iOS apps to integrate CometChat using the SwiftUI UI Kit and SDK.
Provides a no-code widget for adding chat to Webflow sites.
Offers a no-code widget for embedding chat into Wix websites.
Enables a no-code widget integration for adding chat to WordPress sites.
Add real-time chat, voice, video, and moderation to your app through your AI coding agent.
Docs • CometChat • Get an account (free, 100 MAU)
CometChat's first-party MCP server. Connect Claude, Cursor, Windsurf, VS Code Copilot, Codex, or any other Model Context Protocol–compatible agent and integrate CometChat into your app from natural-language prompts.
Ask the agent: "add a chat tab where users can DM each other" — it reads CometChat's documentation, picks the right components for your stack, and writes the integration code.
Read-only. No account, no API key, no authentication required.
An AI agent reading CometChat's docs and writing a working chat integration from a single prompt.
Related MCP server: ElevenLabs MCP Server
Agent | How to add |
Claude.ai / Claude Desktop | Settings → Connectors → Add custom connector → URL: |
Cursor |
|
Windsurf | Plugins (hammer icon) → Manage plugins → View raw config → paste config below |
VS Code (Copilot Agent) |
|
Claude Code (CLI) |
|
Smithery |
|
Codex CLI |
|
{
"mcpServers": {
"cometchat": {
"url": "https://mcp.cometchat.com/mcp"
}
}
}After connecting, prompt your agent with any of these:
"How do I install the React UI Kit in my Vite project?"
"Walk me through multi-tenant chat for a Next.js SaaS where workspaces are isolated."
"Show me how to add presence indicators and typing dots to my iOS conversation list."
"Set up content moderation so banned words are blocked before delivery."
"Build a no-code chat widget for my Webflow site."
"What's the rate limit for sending messages, and what error code do I get when I hit it?"
The agent reads CometChat's documentation, pulls the relevant implementation bundle, and writes the integration code into your project.
search_cometchat_docs — Search across SDK guides, UI Kit references, REST API documentation, and OpenAPI specs. Returns ranked snippets with titles + direct links. Optional version filter.
fetch_cometchat_doc_page — Fetch the full content of any documentation page as markdown by URL or relative path.
get_cometchat_implementation_bundle — Return a curated implementation bundle for a named scenario — prerequisites, install commands, configuration, working code.
list_cometchat_bundles — List every available implementation bundle (identifier, title, framework, last-verified date) for discovery.
All four carry readOnlyHint: true, a title annotation, and a declared outputSchema with structured results. Names are ≤ 64 characters. Descriptions describe contracts only — no behavioral instructions to the agent, no cross-tool routing, no marketing language.
URI | Purpose |
| Agent orientation skill — Product summary, decision guidance, workflow, common gotchas, verification checklist |
| React UI Kit install + init + login + chat surface |
| React Native UI Kit with navigation and chat screen |
| Flutter UI Kit install + init + basic chat |
| iOS UI Kit (SwiftUI) install + chat view |
| Android UI Kit (Jetpack Compose) install + chat screen |
| Vanilla JS SDK — send/receive text and media messages |
| No-code widget embed for HTML, Squarespace, Webflow, Wix, WordPress, Shopify |
| AI moderation rules, image moderation, webhooks |
| Multi-tenant SaaS chat — tenant isolation, server-issued Auth Tokens |
| Online presence, typing indicators, read receipts |
You prompt your agent in natural language.
The agent reads the orientation skill (cometchat://skills/overview) to understand which tool/bundle fits your request.
For top scenarios, the agent pulls a curated implementation bundle — ready-to-run code with prerequisites, install commands, configuration, and working examples.
For long-tail questions, the agent searches CometChat's docs and reads specific reference pages.
The agent writes the code into your project, using the bundle as the source of truth and your project structure as the constraint.
CometChat is a real-time communications platform for adding chat, voice, and video calling to web and mobile apps. Used in production across SaaS, marketplaces, gaming, healthcare, education, and creator platforms.
Free tier: first 100 monthly active users, no credit card required.
SDKs: JavaScript, React Native, iOS, Android, Flutter.
UI Kits: React, React Native, iOS, Android, Flutter, Angular, Vue.
No-code: chat widget for any HTML site.
Sign up: app.cometchat.com — you'll need an App ID, Auth Key, and Region to build with the code the agent writes.
Field | Value |
Display name | CometChat Docs |
Version | 0.1.6 |
Protocol | MCP |
Transport | Streamable HTTP (with SSE) |
Authentication | None (public docs only) |
Capabilities |
|
Health endpoint |
|
Your agent (Claude / Cursor / Windsurf / …)
↓ MCP over Streamable HTTP
↓
mcp.cometchat.com/mcp (this server)
↓
├── search_cometchat_docs → SQLite FTS5 index of cometchat/docs
├── fetch_cometchat_doc_page → cometchat.com/docs/*.md (first-party)
└── get_cometchat_implementation_bundle → bundled markdown recipesStateless server, single universal endpoint, no user-specific state.
Search index rebuilds from github.com/cometchat/docs on every push to that repo's main branch.
Implementation bundles carry a last_verified date and are re-checked against live SDK versions quarterly.
# Clone the docs repo (used to build the search index)
git clone --depth 1 https://github.com/cometchat/docs.git ../cometchat-docs-repo
# Install + build the FTS index + run the server
npm install
DOCS_REPO=../cometchat-docs-repo npm run build:index
npm run dev
# Run the test suite (36 tests across validation, truncation, bundles, tools, resources, fetch)
npm testThe server listens on http://0.0.0.0:3000 by default. Health probe at GET /health, MCP endpoint at POST /mcp.
npx @modelcontextprotocol/inspector
# add server: http://localhost:3000/mcpYou should see all 4 tools with readOnlyHint: true and all 11 resources.
docs-mcp/
├── src/
│ ├── server.ts # MCP server entry, transport, tool dispatch
│ ├── tools/{search,fetch,bundle}.ts
│ ├── search/sqlite.ts # SQLite FTS5 client
│ ├── bundles/loader.ts # markdown bundle store
│ ├── resources/registry.ts # skill + bundle resources
│ └── lib/{errors,truncate,validation,logger}.ts
├── scripts/build-index.ts # builds SQLite FTS5 index from cometchat/docs
├── bundles/ # 10 curated implementation bundles
├── skills/overview.md # agent orientation skill
├── tests/ # vitest suite
├── .claude-plugin/
│ ├── plugin.json # Claude Code plugin manifest
│ └── marketplace.json # Claude Code marketplace manifest
├── .codex-plugin/plugin.json # Codex plugin manifest
├── .cursor-plugin/plugin.json # Cursor Marketplace manifest
├── .mcp.json # MCP config (Claude Code auto-discovery)
├── mcp.json # Open Plugins standard manifest
└── assets/logo.svg # CometChat logoEnv var | Default | Notes |
|
| HTTP port |
|
| Bind host |
|
| Used for URLs in responses + the |
|
| SQLite FTS5 index location. Server still boots if missing; search returns |
|
| Markdown bundles directory |
|
| Orientation skill ( |
|
| Per-fetch HTTP timeout |
|
|
|
|
|
|
|
| Comma-separated |
| unset | Comma-separated CORS origin allowlist |
|
| Set |
|
| Set |
|
| Max requests per window per IP |
|
| Rate-limit window in ms |
|
| Set |
|
| How often to check the docs repo for a new commit (a |
|
| Where rebuilt index generations are written (tmpfs in production) |
|
| Previous index generations retained on disk for instant fallback |
|
| Absolute floor: a candidate index with fewer pages is rejected |
|
| Relative floor: reject a candidate losing more than this fraction of the served page count |
|
| Public docs repo; cloned anonymously, no credentials |
|
| Branch to follow |
| unset | Freeze on one commit and stop following |
| unset | PostHog project API key. Unset = usage analytics fully disabled (no-op) |
|
| PostHog instance host |
| unset | Required when |
See DEPLOY.md for container build, environment, and platform notes.
The same server URL is listed across multiple agent marketplaces:
Marketplace | Listing |
Smithery | |
Glama | |
Cursor Marketplace |
|
Cursor Directory |
|
Anthropic Connector Directory |
|
Codex Marketplace |
|
Issues / feedback: open an issue in this repo.
CometChat support: support@cometchat.com.
Live MCP status: curl https://mcp.cometchat.com/health returns {"status":"ok"} when healthy.
PRs welcome — especially:
New implementation bundles for under-served scenarios (drop a markdown file in bundles/ with the required frontmatter).
Bundle refreshes when SDK versions change (last_verified date in the bundle's frontmatter triggers a CI warning if older than 6 months).
Tool improvements behind the existing read-only contract.
Out of scope today:
Tools that write to a customer's CometChat app (separate authenticated connector, on the roadmap).
Mixed read/write tools (Anthropic auto-rejection rule).
The CometChat MCP server is read-only and requires no account, API key, or authentication. It serves only CometChat's public documentation and does not request, store, or transmit your code, prompts, or personal data. Standard request metadata (such as IP address) may be processed transiently for rate limiting and abuse prevention.
For full details, see CometChat's privacy policy: cometchat.com/legal-privacy-policy.
Apache-2.0. See LICENSE.
Fetches the full content of a single CometChat documentation page by URL or path. Returns the page content as markdown along with title and section metadata. Path can be passed as a full https://www.cometchat.com/docs URL or as a relative path such as '/sdk/javascript/overview'.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Documentation path or full URL. Relative paths like '/sdk/javascript/overview' and full URLs both work. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare readOnlyHint=true, confirming the tool is safe. The description adds value by stating the return format (markdown) and metadata (title, section), which is beneficial beyond the annotation. No side effects or rate limits are mentioned, but for a simple read tool this is sufficient.
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 consists of two well-structured sentences with no extraneous information. The first sentence states the core function and output, the second clarifies input format. Every word earns its place.
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 low complexity (1 parameter, simple read operation, annotations present, no output schema), the description is fully adequate. It covers the tool's purpose, input options, and output type, leaving no obvious gaps for an AI agent to misunderstand.
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?
Schema coverage is 100% for the single parameter 'path'. The description adds further clarity with concrete examples (full URL and relative path), which enhances understanding beyond the schema's description. This justifies a score above the baseline of 3.
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 fetches the full content of a single CometChat documentation page, distinguishing it from sibling tools like search (which returns snippets) and implementation bundle (different resource). The verb 'fetches' paired with 'documentation page' is specific and unambiguous.
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 explains the input format (URL or path) with examples, but does not provide explicit guidance on when to use this tool versus its siblings (e.g., 'Use this when you need the full page content'). The usage is implied by the purpose, but no alternatives or exclusions are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Returns a curated implementation bundle for a named CometChat integration scenario. Each bundle includes prerequisites, install commands, configuration, working code examples, and common pitfalls. Available bundles cover common integration patterns across React, Flutter, iOS, Android, React Native, and the JavaScript SDK.
| Name | Required | Description | Default |
|---|---|---|---|
| bundle | Yes | Bundle name in lowercase kebab-case, e.g. 'react-uikit-quickstart'. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true. The description adds behavioral context by detailing what the bundle includes (prerequisites, commands, code examples, pitfalls), which goes beyond the annotation. 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences that front-load the core purpose and follow with useful detail. No extraneous words; every sentence earns its place.
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 simplicity (1 parameter, no output schema), the description covers what to expect from the output. It lacks explicit format details but is sufficient for an agent to understand and invoke the tool correctly.
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?
Schema description coverage is 100%. The description mentions 'named CometChat integration scenario' and lists example platforms, reinforcing the parameter's purpose but not adding significant new information beyond 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 tool returns a curated implementation bundle for a named integration scenario, listing included components. It distinguishes from sibling tools (fetch doc page, search docs) by focusing on bundles.
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 when to use the tool (when needing an implementation bundle) but does not explicitly state when not to use it or provide direct comparison to sibling tools. Usage context is implied but not fully explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Searches CometChat documentation including SDK guides (JavaScript, React, iOS, Android, Flutter, React Native), UI Kit references, REST API documentation, integration tutorials, and OpenAPI specs. Returns ranked snippets with titles and direct links to source pages. Supports an optional version filter to scope results to a specific documentation version.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of results to return. Default 10, maximum 25. | |
| query | Yes | Search query. 1–500 characters. | |
| version | No | Optional documentation version filter, e.g. 'v4' or 'v3'. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, so description does not need to reiterate safety. The description adds that it returns ranked snippets with titles and direct links, which is useful but not rich behavioral context beyond what a search tool implies.
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?
Three concise sentences: first captures purpose and scope, second describes output format, third mentions the optional version filter. No redundancies, well front-loaded, and every sentence serves a clear function.
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 100% schema coverage and clear annotations, the description covers output format and the version filter. It does not explain pagination behavior for the `limit` parameter, but that is minimal. Overall sufficient for a search tool without output schema.
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?
Schema coverage is 100% with descriptions for all parameters. The description adds value by listing the content domains searched (SDK guides, UI Kit, etc.), which clarifies what the query parameter targets. No additional semantics for `limit` or `version` beyond 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?
Clearly lists the verb 'searches' and the resource 'CometChat documentation' with an extensive enumeration of covered content types (SDK guides, UI Kit, REST API, etc.). Distinguishes from sibling tools implicitly by focusing on search vs. fetch or implementation retrieval.
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?
No explicit guidance on when to use this tool over siblings (fetch_cometchat_doc_page, get_cometchat_implementation_bundle). Does not mention when not to use it or provide context for alternative tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.5fetch_cometchat_doc_pageget_cometchat_implementation_bundlesearch_cometchat_docsEach tool has a clearly distinct purpose: fetching a specific page, retrieving a curated implementation bundle, and searching across documentation. No overlap in functionality.
All tool names follow a consistent verb_noun pattern (fetch_page, get_bundle, search_docs) with clear prefixes, making them predictable and easy to understand.
With 3 tools, the set is slightly lean but still well-scoped for a documentation server. Each tool addresses a distinct need without redundancy.
The tools cover fetching, searching, and getting implementation examples. Missing a tool to list available bundles or documentation sections, but search can mitigate this gap.
Search @imqueue docs and scaffold typed services & clients from your AI coding agent.
Helps AI coding agents integrate MetaMask Embedded Wallets (Web3Auth) SDKs.
Create and manage AI agents that collaborate and solve problems through natural language interacti…
Free live chat and AI support agent. Auto-create a workspace and embed from your AI editor.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/cometchat/docs-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
