SignalSAFE
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
An MCP integration for signal-cli that allows AI agents to send and receive Signal messages.
Features
- Send messages to Signal users
- Send messages to Signal groups
- Receive and parse incoming messages
- Async support with timeout handling
- Detailed logging
Prerequisites
This project requires signal-cli to be installed and configured on your system.
Installing signal-cli
- Install signal-cli: Follow the official installation instructions
- Register your Signal account:
signal-cli -u YOUR_PHONE_NUMBER register
- Verify your account with the code received via SMS:
signal-cli -u YOUR_PHONE_NUMBER verify CODE_RECEIVED
For more detailed setup instructions, see the signal-cli documentation.
Installation
pip install -e . # or use uv for faster installation uv pip install -e .
Usage
Run the MCP server:
./main.py --user-id YOUR_PHONE_NUMBER [--transport {sse|stdio}]API
Tools Available
send_message_to_user: Send a direct message to a Signal usersend_message_to_group: Send a message to a Signal groupreceive_message: Wait for and receive messages with timeout support
Development
This project uses:
- MCP for agent-API integration
- Modern Python async patterns
- Type annotations throughout
dbf231db2715OBSERVED · 2026-10-09Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add signal-mcp -- uvx signal-mcp
{
"mcpServers": {
"signal-mcp": {
"command": "uvx",
"args": [
"signal-mcp"
]
}
}
}Exposed tools (3)
1 read · 2 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
receive_message | read | Wait for and receive a message using signal-cli. |
send_message_to_group | write | Send a message to a group using signal-cli. |
send_message_to_user | write | Send a message to a specific user using signal-cli. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (1)
Gates applied: no_behavioural_pass, no_license.
dbf231db2715full audit observations/trust-audit/mcp-server/rymurr__signal.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-09 | dbf231db2715 | SAFE | B | 89 | first audit |
Questions
What tools does Signal expose?
3 in total: 1 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Signal safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Signal need?
No credential environment variables were found in its source, so it appears to need none.
How current is this page?
The grade is for one exact copy of the source (dbf231db2715), read on 2026-10-09. The repository is watched and re-audited when it changes.