classifinder-mcp
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CLASSIFINDER_API_KEY | Yes | Your ClassiFinder API key. Get one at https://classifinder.ai | |
| CLASSIFINDER_MCP_AUDIT | No | Set to '0' to disable audit logging | 1 |
| CLASSIFINDER_MCP_AUDIT_PATH | No | Override the audit log path | ~/.classifinder/mcp-audit.log |
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 | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| classifinder_scanA | Scan text for leaked secrets and credentials. Returns structured findings with type, severity, confidence, and remediation guidance. Use this to check if text contains API keys, passwords, tokens, or other sensitive credentials. Args: text: The text to scan for secrets. min_confidence: Minimum confidence threshold (0.0-1.0). Default 0.5. |
| classifinder_redactA | Scan text and replace all detected secrets with safe placeholders. Returns clean text safe to forward to any LLM or logging system. Use this before sending user input to a model. Args: text: The text to redact. redaction_style: How to replace secrets. Options: "label" - [AWS_ACCESS_KEY_REDACTED] (default) "mask" - AKIA************** "hash" - [REDACTED:sha256:a1b2c3d4] |
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 2 tools
The two tools have clearly distinct purposes: scan detects secrets, redact replaces them. There is no overlap in functionality.
Both tools follow the consistent pattern 'classifinder_<verb>', using snake_case and descriptive verbs (scan, redact).
With only two tools, the set is minimal but appropriate for a focused secrets-handling utility. Could potentially include a 'classify' tool, but current scope is clear.
The pair covers the full workflow: scanning for secrets and redacting them. No obvious missing operations for the stated purpose.