Skip to main content
Glama
rosquillas

Element MCP Server

by rosquillas
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Remote

Element MCP Server

License: MIT Node.js MCP

An MCP (Model Context Protocol) server that connects Claude with Element. Read rooms, messages, and search content in your Matrix conversations.

🌐 También disponible en español más abajo / Spanish version below

What is this?

This server acts as a "bridge" between Claude and your Matrix account. Once configured, Claude can:

  • List your Matrix rooms

  • Read messages from any room

  • Search messages by content

  • View detailed room information

Related MCP server: google-chat-mcp

Prerequisites

  • Node.js 18+ installed

  • A Matrix account (e.g., on matrix.org or Element)

  • Your Matrix Access Token

Getting your Access Token

From Element Web/Desktop:

  1. Open Element and go to Settings (gear icon)

  2. Go to Help & About

  3. In the advanced section, find Access Token

  4. Copy the token (starts with something like syt_... or MDAxO...)

⚠️ Important: Your access token is like a password. Don't share it publicly.

Installation

# Clone the repository
git clone https://github.com/rosquillas/matrix-mcp-server.git
cd matrix-mcp-server

# Install dependencies
npm install

# Build the project
npm run build

Configuration

Environment Variables

# Your Matrix homeserver (default: https://matrix.org)
MATRIX_HOMESERVER=https://matrix.org

# Your access token (REQUIRED)
MATRIX_ACCESS_TOKEN=your_token_here

# Transport type: 'stdio' or 'http' (default: stdio)
TRANSPORT=stdio

# Port for HTTP mode (default: 3000)
PORT=3000

Usage

stdio mode (recommended for Claude Desktop)

MATRIX_ACCESS_TOKEN=your_token npm start

HTTP mode (for remote use)

TRANSPORT=http MATRIX_ACCESS_TOKEN=your_token npm start

Claude Desktop Configuration

Add this to your Claude Desktop config file:

  • Mac: ~/Library/Application Support/Claude/claude_desktop_config.json

  • Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "matrix": {
      "command": "node",
      "args": ["/path/to/matrix-mcp-server/dist/index.js"],
      "env": {
        "MATRIX_HOMESERVER": "https://matrix.org",
        "MATRIX_ACCESS_TOKEN": "your_token_here"
      }
    }
  }
}

Available Tools

matrix_list_rooms

List all rooms you've joined.

Parameters:

  • limit (optional): Maximum number of rooms (1-100, default: 20)

matrix_get_messages

Get messages from a specific room.

Parameters:

  • room_id (required): Room ID (e.g., !abc123:matrix.org)

  • limit (optional): Number of messages (1-100, default: 50)

  • direction (optional): 'b' for older, 'f' for newer

matrix_search_messages

Search messages by content.

Parameters:

  • query (required): Text to search

  • room_id (optional): Limit to a specific room

  • limit (optional): Max results (1-50, default: 10)

matrix_get_room_info

Get detailed room information.

Parameters:

  • room_id (required): Room ID

Example Usage

Once configured, you can tell Claude:

"Show me my Matrix rooms"

"What was discussed yesterday in the development room?"

"Search for messages about 'deployment' in my chats"

Security

  • Access token is passed as environment variable, never stored in code

  • Only read operations (cannot send messages)

  • Server only communicates with your configured homeserver

Troubleshooting

"MATRIX_ACCESS_TOKEN environment variable is required"

Make sure to set the environment variable with your token.

"Matrix API error (401)"

Your token expired or is invalid. Generate a new one from Element.

"Matrix API error (403)"

You don't have permissions to access that room.

Versión en Español

¿Qué es esto?

Este servidor actúa como un "puente" entre Claude y tu cuenta de Matrix. Una vez configurado, Claude puede:

  • Ver tus salas de Matrix

  • Leer mensajes de cualquier sala

  • Buscar mensajes por contenido

  • Ver información detallada de las salas

Requisitos Previos

  • Node.js 18+ instalado

  • Una cuenta de Matrix (por ejemplo, en matrix.org o Element)

  • Tu Access Token de Matrix

Obtener tu Access Token

Desde Element Web/Desktop:

  1. Abre Element y ve a Configuración (ícono de engrane)

  2. Ve a Ayuda y Sobre (Help & About)

  3. En la sección avanzada, encontrarás Access Token

  4. Copia el token (empieza con algo como syt_... o MDAxO...)

⚠️ Importante: Tu access token es como una contraseña. No lo compartas públicamente.

Instalación

# Clona el repositorio
git clone https://github.com/rosquillas/matrix-mcp-server.git
cd matrix-mcp-server

# Instala dependencias
npm install

# Compila el proyecto
npm run build

Configuración con Claude Desktop

Agrega esto a tu archivo de configuración:

  • Mac: ~/Library/Application Support/Claude/claude_desktop_config.json

  • Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "matrix": {
      "command": "node",
      "args": ["/ruta/a/matrix-mcp-server/dist/index.js"],
      "env": {
        "MATRIX_HOMESERVER": "https://matrix.org",
        "MATRIX_ACCESS_TOKEN": "tu_token_aqui"
      }
    }
  }
}

License

MIT

Available Tools

4 tools
matrix_get_messagesGet Matrix MessagesA
Read-onlyIdempotent

Retrieve messages from a specific Matrix room.

Use matrix_list_rooms first to get available room IDs.

Args:

  • room_id: The room ID to fetch messages from

  • limit: Maximum messages to return (1-100, default 50)

  • from: Pagination token for fetching more messages

  • direction: 'b' for older messages, 'f' for newer

Returns:

  • List of messages with sender, timestamp, and content

  • Pagination tokens for fetching more messages

ParametersJSON Schema
NameRequiredDescriptionDefault
room_idYesThe Matrix room ID (e.g., !abc123:matrix.org)
limitNoMaximum number of messages to return
fromNoPagination token from a previous request (use 'end' value)
directionNoDirection to paginate: 'b' for backwards (older), 'f' for forwards (newer)b

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=true, and idempotentHint=true, covering safety and idempotency. The description adds valuable behavioral context: pagination behavior (tokens, direction options), return format details (list with sender/timestamp/content), and default values (limit default 50), which aren't covered by annotations.

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 well-structured and front-loaded: the first sentence states the core purpose, followed by usage guidance, then parameter explanations, and return details. Every sentence earns its place with no wasted words, making it efficient and scannable.

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?

Given the tool's moderate complexity (4 parameters, pagination), rich annotations (covering safety/idempotency), and 100% schema coverage, the description is complete. It adds necessary context like prerequisite usage, behavioral details (pagination, returns), and distinguishes from siblings, compensating for the lack of output schema by describing return values.

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 100%, so the schema fully documents all parameters. The description adds minimal extra semantics: it clarifies 'from' as a pagination token from previous requests and mentions default values, but doesn't provide significant additional meaning beyond the schema's thorough descriptions.

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 clearly states the verb 'retrieve' and resource 'messages from a specific Matrix room', distinguishing it from siblings like matrix_get_room_info (room metadata), matrix_list_rooms (room listing), and matrix_search_messages (filtered search). It specifies the exact scope of retrieval.

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?

The description explicitly provides when-to-use guidance: 'Use matrix_list_rooms first to get available room IDs.' This directs users to a prerequisite tool and distinguishes it from matrix_search_messages by implying this is for bulk retrieval rather than filtered search.

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

matrix_get_room_infoGet Matrix Room InfoB
Read-onlyIdempotent

Get detailed information about a specific Matrix room.

Returns room name, topic, members, and other state information.

Args:

  • room_id: The room ID to get info for

Returns:

  • Room name, topic, creation info, and member list

ParametersJSON Schema
NameRequiredDescriptionDefault
room_idYesThe Matrix room ID

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=true, and idempotentHint=true, covering safety and idempotency. The description adds context about what information is returned (room name, topic, creation info, member list), which is useful but doesn't disclose behavioral traits like rate limits, authentication needs, or error conditions beyond what annotations provide.

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?

The description is front-loaded with the core purpose, followed by return details and parameter info in a structured format. It's efficient with minimal waste, though the Args and Returns sections slightly duplicate schema information without adding value.

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?

Given the tool's low complexity (1 parameter, no output schema) and rich annotations, the description is adequate but incomplete. It lacks usage guidelines and doesn't fully compensate for the absence of an output schema by detailing return value structures or error handling, leaving gaps for an AI agent.

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 100%, with the parameter 'room_id' fully documented in the schema as 'The Matrix room ID'. The description repeats this information in the Args section without adding meaningful semantics beyond the schema, such as format examples or validation rules.

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 clearly states the verb 'Get' and resource 'detailed information about a specific Matrix room', specifying it returns room name, topic, members, and other state information. However, it doesn't explicitly differentiate from sibling tools like 'matrix_list_rooms' (which likely lists multiple rooms) or 'matrix_get_messages' (which focuses on messages rather than room metadata).

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?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like 'matrix_list_rooms' for listing rooms or 'matrix_get_messages' for message retrieval, nor does it specify prerequisites or contextual constraints for usage.

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

matrix_list_roomsList Matrix RoomsA
Read-onlyIdempotent

List all Matrix rooms that the user has joined.

Returns room IDs, names, and basic information about each room. Use this to discover which rooms are available before fetching messages.

Returns:

  • List of rooms with room_id, name, topic, and member count

  • Use room_id with matrix_get_messages to read messages

ParametersJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum number of rooms to return

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=true, and idempotentHint=true, covering safety and idempotency. The description adds valuable context beyond annotations: it specifies the return format (room IDs, names, topic, member count) and mentions the purpose of discovering rooms before fetching messages, which helps the agent understand the tool's role in a workflow. No contradictions with annotations.

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 front-loaded with the core purpose in the first sentence, followed by return details and usage guidance. Every sentence adds value: the first states what it does, the second specifies returns, and the third provides context for usage. No wasted words or redundancy.

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?

Given the tool's low complexity (one optional parameter), rich annotations (covering safety and idempotency), and no output schema, the description is mostly complete. It explains the purpose, returns, and usage context. A minor gap is lack of explicit mention of pagination or ordering for the list, but annotations (openWorldHint=true) imply scalability, and the limit parameter handles basic control.

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 100%, with the single parameter 'limit' fully documented in the schema (type, range, default). The description does not add any parameter-specific information beyond what the schema provides, so it meets the baseline of 3 for high schema coverage without extra value.

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 clearly states the specific action ('List all Matrix rooms') and resource ('that the user has joined'), distinguishing it from siblings like matrix_get_room_info (which likely gets details for a specific room) and matrix_search_messages (which searches messages rather than listing rooms). It explicitly mentions the verb 'list' and scope 'joined rooms'.

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?

The description provides explicit guidance on when to use this tool ('to discover which rooms are available before fetching messages') and names a specific alternative ('Use room_id with matrix_get_messages to read messages'). It also implies when not to use it (e.g., for room details or message searching, handled by other siblings).

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

matrix_search_messagesSearch Matrix MessagesA
Read-onlyIdempotent

Search for messages across Matrix rooms.

Search for specific content within messages. Can search all rooms or a specific room.

Args:

  • query: Text to search for in messages

  • room_id: Optional room ID to limit search scope

  • limit: Maximum results (1-50, default 10)

Returns:

  • Matching messages with room, sender, and content

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYesSearch query to find in messages
room_idNoOptional: limit search to a specific room
limitNoMaximum number of results to return

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already indicate read-only, open-world, idempotent, and non-destructive behavior, so the description does not need to repeat these. It adds valuable context by specifying the search scope ('all rooms or a specific room') and return format ('Matching messages with room, sender, and content'), enhancing understanding beyond annotations without contradiction.

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 front-loaded with the core purpose, followed by structured 'Args' and 'Returns' sections. Every sentence is necessary and efficient, with no redundant information, making it easy to scan and understand quickly.

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?

Given the tool's moderate complexity, rich annotations, and 100% schema coverage, the description is largely complete. It explains the purpose, usage, parameters, and return values. However, without an output schema, it could benefit from more detail on the structure of returned messages, though the annotations provide safety context.

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 100%, with each parameter well-documented in the schema. The description adds minimal value by summarizing parameters in the 'Args' section but does not provide additional semantics, syntax, or format details beyond what the schema already covers, meeting the baseline for high schema coverage.

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 clearly states the specific action ('Search for messages'), resource ('across Matrix rooms'), and scope ('all rooms or a specific room'), distinguishing it from sibling tools like matrix_get_messages (which likely retrieves messages without search) and matrix_list_rooms (which lists rooms rather than searching within them).

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

Usage Guidelines4/5

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

The description provides clear context for usage ('Search for specific content within messages') and implies when to use it (for searching rather than direct retrieval), but it does not explicitly name alternatives or state when not to use it, such as distinguishing from matrix_get_messages for non-search scenarios.

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

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.9/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose with no overlap: list_rooms discovers available rooms, get_room_info provides room metadata, get_messages retrieves message history, and search_messages performs content searches. The descriptions clearly differentiate these functions, making tool selection unambiguous for an agent.

Naming Consistency5/5

All tools follow a perfect 'matrix_verb_noun' pattern with consistent snake_case throughout: matrix_list_rooms, matrix_get_room_info, matrix_get_messages, and matrix_search_messages. This predictable naming convention makes the tool set highly readable and organized.

Tool Count4/5

Four tools is reasonable for a Matrix server, covering core room discovery, metadata retrieval, message reading, and search functionality. However, the absence of write operations (like sending messages or creating rooms) makes the count feel slightly lean for a complete Matrix integration, though still well-scoped for read-only use cases.

Completeness3/5

The tool set provides excellent read-only coverage for rooms and messages, but lacks any write capabilities (e.g., send_message, create_room, join_room) or room management operations (e.g., leave_room, update_room_info). This creates notable gaps that could limit agent workflows, though the existing tools form a coherent read-only surface.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

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/rosquillas/element-mcp-server'

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