Which integrations are available for this server?

Allows reading and responding to Apple Messages (iMessage) on macOS, including listing chats, retrieving conversation context, fetching unread messages, sending messages, and marking chats as read. Provides tools for interacting with local macOS Messages, enabling AI agents to manage chats and messages on the user's Mac through the Messages app.

How do I use messages-mcp?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@messages-mcp show my recent messages" 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.

messages-mcp

by raghavrat

Overview Schema Source Related Servers Score Discussions Admin

Python

Local

messages-mcp

MCP server for reading and responding to local macOS Messages from clients like Claude Desktop and Codex.

The server reads ~/Library/Messages/chat.db, resolves names through local Contacts/AddressBook source databases, and sends through the macOS Messages app using AppleScript.

Requirements

macOS with Messages configured
Python 3.10+
Full Disk Access for the app running the MCP server
Automation permission for controlling Messages when sending

Related MCP server: imessage-mcp

Install

From this repo:

python3 -m venv .venv
. .venv/bin/activate
pip install -e .

Run manually:

messages-mcp

Claude Desktop

Add this to Claude Desktop's MCP config, adjusting the path:

{
  "mcpServers": {
    "messages": {
      "command": "/Users/YOU/Documents/messages-mcp/.venv/bin/messages-mcp"
    }
  }
}

Restart Claude Desktop after editing the config.

Codex

Use the command path from the virtualenv:

{
  "mcpServers": {
    "messages": {
      "command": "/Users/YOU/Documents/messages-mcp/.venv/bin/messages-mcp"
    }
  }
}

Tools

list_chats(query="", limit=25) List recent chats, optionally filtered by contact name, phone/email, or group name.
get_conversation_context(chat, limit=30) Return recent messages and attachment metadata for a chat. chat can be a contact name, phone/email, or group name.
get_unread_messages(chat="", limit=20) Return unread incoming messages for one chat or all recent chats.
send_message(chat, text, dry_run=true) Send a message through Messages. dry_run defaults to true; pass false to actually send.
mark_read(chat) Best-effort mark a chat as read through Messages.

Safety

Sending is intentionally explicit. The send_message tool defaults to dry_run=true, so clients can inspect the target and text before sending.

Do not run this server for an MCP client you do not trust. Any connected client with tool access can read local Messages context and, if it calls send_message(..., dry_run=false), send messages through your account.

Troubleshooting

If chats do not appear:

Give the MCP host app Full Disk Access.
Use a contact name for one-on-one chats.
Use the exact group chat title for group chats.
Make sure Messages is signed in and synced locally.

If sending fails:

Open Messages once manually.
Approve the Automation permission prompt.
Try send_message(..., dry_run=true) first to verify the resolved target.

Available Tools

5 tools

get_conversation_contextC

Return recent conversation context for a chat. Prefer contact names for direct chats and group titles for groups.

ParametersJSON Schema

Name	Required	Description	Default
`chat`	Yes
`limit`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

C2.3/5.0

Behavior2/5

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

No annotations are provided, so the description must disclose behavioral traits. It mentions that contact names are preferred for direct chats and group titles for groups, which gives a clue about output formatting. However, it does not state that the operation is read-only, whether it requires authentication, or what the 'context' includes. Critical behavioral information is missing.

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 concise at two sentences, with the first stating the purpose and the second adding a relevant detail (naming preference). The structure is clear and front-loaded, but it could include critical parameter information without becoming overly long.

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

Completeness2/5

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

Given the tool has two parameters, no schema documentation, and no annotations, the description is insufficiently complete. It does not explain what the output contains (though an output schema exists, per rules it's not required in description). Parameter semantics and behavioral context are missing, leaving significant gaps for an agent to use the tool effectively.

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

Parameters1/5

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

The input schema has two parameters (chat, limit) with no descriptions (0% schema coverage). The tool description does not explain what 'chat' represents or what 'limit' controls. This leaves the agent guessing about parameter meanings, making correct invocation difficult.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states 'Return recent conversation context for a chat,' which identifies a specific operation and resource. However, 'context' is somewhat vague; it could mean recent messages, participants, or other metadata. It distinguishes itself from sibling tools like get_unread_messages and list_chats, but the exact scope is unclear.

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 (e.g., get_unread_messages, list_chats). It does not mention prerequisites, limitations, or scenarios where it is preferred. The only hint is the naming preference, but that is not about usage context.

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

get_unread_messagesB

Return unread incoming messages. If chat is empty, checks recent chats.

ParametersJSON Schema

Name	Required	Description	Default
`chat`	No
`limit`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

B3/5.0

Behavior3/5

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

With no annotations, the description carries full burden. It discloses the fallback behavior when chat is empty, which is useful. However, it omits other important behaviors such as whether the action is read-only, authentication requirements, or rate limits.

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 short (two sentences) and front-loaded with the main action. It is concise, but at the expense of missing necessary details; however, the structure is clear and efficient.

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

Completeness2/5

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

Despite having an output schema, the description is too brief for a tool with two parameters and sibling tools. It does not explain parameter usage or when to choose this tool over others, leaving gaps for the agent.

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

Parameters1/5

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

Schema description coverage is 0%, and the description does not explain the two parameters (chat and limit) at all. It adds no meaning beyond the schema's default values, leaving the agent unaware of parameter purpose or format.

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 tool returns unread incoming messages, with a specific verb and resource. It also adds a nuance about fallback behavior when chat is empty, which helps distinguish it from sibling tools like list_chats and send_message.

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?

No guidance is provided on when to use this tool versus alternatives (e.g., get_conversation_context for full history or mark_read for marking). The description lacks explicit usage context or conditions.

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

list_chatsB

List recent Messages chats, optionally filtered by contact name, phone/email, or group name.

ParametersJSON Schema

Name	Required	Description	Default
`limit`	No
`query`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

B3.3/5.0

Behavior2/5

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

No annotations provided, so description carries full burden. Only states it lists 'recent' chats with filtering; no disclosure of side effects, privacy, or ordering. Lacks behavioral traits like read-only assurance.

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?

Single sentence with no redundancy. Front-loads purpose and filtering capability. Every word earns its place.

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?

Minimal description for a simple tool. Lacks details on ordering, default limit meaning, or pagination. Output schema exists but description could still clarify 'recent' timeframe. Adequate but not rich.

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 has 0% description coverage. Description explains query parameter (filter by name/phone/email/group) but does not add meaning to limit parameter (only default given). Partially compensates for one parameter.

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?

Description clearly states 'list recent Messages chats' with optional filtering, distinguishing it from sibling tools like get_conversation_context which focuses on a single chat's details. Verb (list) and resource (chats) are specific.

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?

No guidance on when to use this tool versus siblings. Implicitly it's for listing chats, but no explicit when-not or alternatives mentioned.

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

mark_readC

Best-effort mark a chat read through macOS Messages.

ParametersJSON Schema

Name	Required	Description	Default
`chat`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

C2.7/5.0

Behavior2/5

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

The description only mentions 'best-effort' which hints at unreliable behavior, but does not elaborate on failure conditions, side effects, or required permissions. With no annotations provided, the description carries full burden but falls short.

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

Conciseness3/5

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

The description is very brief (one sentence), which is concise but at the cost of missing critical details. It could be expanded slightly to cover parameter guidance and usage without becoming verbose.

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

Completeness2/5

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

Despite low tool complexity (one required param, no nested objects), the description lacks completeness. It does not explain return values, behavior under failure, or how the 'best-effort' nature impacts the agent's decision. The existence of an output schema is mentioned in context signals, so return values are partially covered, but the description adds little.

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

Parameters1/5

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

The only parameter 'chat' is described only by its schema (type string, required). The description adds no information about format, source, or meaning beyond the schema. Given 0% schema description coverage, the tool definition provides no help for agents to construct valid input.

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 action ('mark read') and the resource ('chat'), and includes the scope ('through macOS Messages'). It implicitly distinguishes itself from siblings like get_unread_messages or send_message by specifying a mutation action.

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?

No explicit guidance on when to use or not use this tool, no mention of prerequisites or alternatives. The 'best-effort' qualifier hints at limitations but doesn't clarify when it might fail or suggest other tools.

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

send_messageC

Send a message to a chat through macOS Messages. dry_run defaults to true for safety.

ParametersJSON Schema

Name	Required	Description	Default
`chat`	Yes
`text`	Yes
`dry_run`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

C2.9/5.0

Behavior2/5

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

With no annotations, description carries full burden. Mentions dry_run default for safety, but does not disclose that sending is a write/destructive operation, failure modes, or any side effects.

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

Conciseness3/5

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

Two sentences, no waste, but under-specified. Concise at the expense of completeness.

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

Completeness2/5

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

Lacks details on chat format, output behavior, prerequisites, or error conditions. Output schema exists but not utilized in description. Inadequate for a write tool with 3 parameters.

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

Parameters2/5

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

Schema description coverage is 0%, so description must add meaning. Only mentions dry_run default; chat and text are not explained. 'Chat' is ambiguous (ID vs name). Poor compensation for missing schema 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?

Clearly states verb 'Send', resource 'message', and context 'to a chat through macOS Messages'. Distinguishes from siblings which are read/list/mark operations.

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?

No guidance on when to use this tool versus alternatives. Only mentions dry_run default for safety, but does not explain when to switch dry_run off or distinguish from sibling tools.

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.

5 tool updatesv0.1.0Jul 9, 2026
- First observedget_conversation_context
- First observedget_unread_messages
- First observedlist_chats
- First observedmark_read
- First observedsend_message

Install Server

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

TDQS

B3.3/5.0

Scored 2026-07-09 21:30 across 5 tools

Disambiguation5/5

Each tool targets a distinct operation: retrieving context, unread messages, listing chats, marking read, and sending. No overlap in functionality.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern in snake_case (e.g., get_conversation_context, list_chats), making the set predictable.

Tool Count5/5

Five tools is well-scoped for a messaging server, providing core functionality without unnecessary bloat or gaps.

Completeness4/5

The set covers essential operations (reading, listing, sending, marking read) but is missing features like deleting messages or fetching specific conversation details, which are minor gaps.

Maintenance

ActivityStale

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

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

Related MCP Connectors

messages-bridgeOAuth
io.github.IsaiahDupree
MCP connector for iMessage & Contacts via a local Mac agent + Vercel relay
Communication App Automation
1
notesbridgeOAuth
io.github.IsaiahDupree
Search, read, and write your Apple Notes from ChatGPT/Claude via a local Mac agent + MCP relay.
Note Taking App Automation
1
hithereiamaliff-mcp-nextcloudOAuth
ai.smithery
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Cloud Storage File Systems Workplace & Productivity
237
QuallaaOAuth
com.quallaa
Talk to your public-facing AI from any MCP client — Claude, ChatGPT, Cursor, Cline, Windsurf.
AI & Machine Learning Communication
2

Related MCP Servers

iMCP
Communication Calendar Management Location Services
mattt
A
license
Not graded
quality
A
maintenance
A macOS app that provides an MCP server to your Messages, Contacts, and more
Updated 3 days ago (2026-09-08 18:22 UTC)
1,539
MIT
imessage-mcp
Communication OS Automation App Automation
camfortin
A
license
A
quality
C
maintenance
A local MCP server that enables reading iMessage conversations and sending new messages through Claude Desktop. It provides secure, read-only access to your Mac's iMessage database and AppleScript-based message sending capabilities.
Updated 17 days ago (2026-08-25 18:42 UTC)
6
MIT
imessage-mcp
Communication Databases
jaredmoskowitz
F
license
A
quality
D
maintenance
A read-only MCP server that exposes your iMessage data to Claude Code and Claude Desktop, with automatic contact name resolution.
Updated 3 months ago (2026-05-30 01:47 UTC)
3
-
imessage-mcp-server
Communication
tinyxia
A
license
Not graded
quality
B
maintenance
MCP server for reading and sending iMessages on macOS. Exposes iMessage history and send capabilities through tools like list_conversations and send_imessage.
Updated 2 months ago (2026-06-28 12:33 UTC)
13
MIT