@1claw/mcp
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | HTTP port (httpStream mode only). | 8080 |
| MCP_TRANSPORT | No | Transport mode: 'stdio' or 'httpStream'. | stdio |
| ONECLAW_AGENT_ID | No | Agent UUID from dashboard. Use with ONECLAW_AGENT_API_KEY. | |
| ONECLAW_BASE_URL | No | Vault API base URL. | https://api.1claw.xyz |
| ONECLAW_VAULT_ID | No | UUID of the vault to operate on. | |
| ONECLAW_LOCAL_ONLY | No | Set to 'true' for security-only mode (no vault credentials needed). | false |
| ONECLAW_AGENT_TOKEN | No | Static Bearer JWT (alternative to ID+key; expires in ~1 h). | |
| ONECLAW_AGENT_API_KEY | No | Agent API key (ocv_...). Server exchanges this for a JWT and auto-refreshes. | |
| ONECLAW_MCP_PII_DETECTION | No | 'true' to detect PII patterns. | true |
| ONECLAW_MCP_REDACT_SECRETS | No | 'true' to redact secret values from non-secret tool outputs. | true |
| ONECLAW_MCP_EXFIL_PROTECTION | No | 'block', 'warn', or 'off'. | block |
| ONECLAW_MCP_SECURITY_ENABLED | No | Master switch. Set to 'false' to disable all inspection. | true |
| ONECLAW_MCP_SANITIZATION_MODE | No | 'block', 'surgical', or 'log_only'. | block |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
| logging | {} |
| completions | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| inspect_contentA | Inspect text content for security threats including command injection, encoding obfuscation, social engineering, and PII. Returns a JSON threat report (safe, verdict, threat_count, threats). Use before processing untrusted input. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
With only one tool, there is no possibility of confusion between tools. The tool's purpose is clear and distinct, leaving no ambiguity.
A single tool name 'inspect_content' follows a clear verb_noun pattern, and with no other tools to compare against, consistency is irrelevant.
One tool is borderline for a server claiming to handle multiple threat detection types. While the tool is not trivial, the scope feels thin for the described purpose.
The server only offers inspection capabilities. Missing tools for remediation, sanitization, or further analysis create significant gaps for a security workflow.