Skip to main content
Glama

Tinplate Edge AI Safety, Security & EU Compliance

tinplate_secret_scanner

Read-onlyIdempotent

Log Redact & Secret Scanner API: Detect and mask leaked API keys, JWTs, and private keys in logs, diffs, and prompts. (Endpoint: POST /v1/secret-scanner)

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "text": "<text>"
    },
    "name": "tinplate_secret_scanner"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNo'token' replaces each unique secret with [SECRET_<TYPE>_<N>] and returns a caller-only map; 'mask' replaces with [REDACTED:<TYPE>]; 'partial' preserves a short prefix/suffix.token
textYesRaw log output, .env file, code snippet, or unified git diff to scan.
typesNoOptional allowlist of secret types to scan for. Scans all 28 types when omitted.
min_entropyNoMinimum Shannon entropy (bits/char) required for GENERIC_HIGH_ENTROPY matches.
diff_only_addedNoWhen true on a unified git diff, ignores removed lines ('-...') and only scans added/context lines.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / additionalProperties
      Added value: +false
  2. Changed1 schema field changed
    • changedInput schema / properties / types / description
      Previous value: -"Optional allowlist of secret types to scan for. Scans all 18 types when omitted."New value: +"Optional allowlist of secret types to scan for. Scans all 28 types when omitted."
  3. Changed10 schema fields changed
    • addedInput schema / properties / diff_only_added
      Added value: +{
      +  "default": false,
      +  "description": "When true on a unified git diff, ignores removed lines ('-...') and only scans added/context lines.",
      +  "example": false,
      +  "type": "boolean"
      +}
    • addedInput schema / properties / min_entropy
      Added value: +{
      +  "default": 3.8,
      +  "description": "Minimum Shannon entropy (bits/char) required for GENERIC_HIGH_ENTROPY matches.",
      +  "example": 3.8,
      +  "maximum": 6,
      +  "minimum": 2.5,
      +  "type": "number"
      +}
    • addedInput schema / properties / mode
      Added value: +{
      +  "default": "token",
      +  "description": "'token' replaces each unique secret with [SECRET_<TYPE>_<N>] and returns a caller-only map; 'mask' replaces with [REDACTED:<TYPE>]; 'partial' preserves a short prefix/suffix.",
      +  "enum": [
      +    "token",
      +    "mask",
      +    "partial"
      +  ],
      +  "example": "token",
      +  "type": "string"
      +}
    • removedInput schema / properties / redact
      Removed value: -{
      -  "description": "Boolean flag 'redact' (default: true)",
      -  "type": "boolean"
      -}
    • changedInput schema / properties / text / description
      Previous value: -"Parameter 'text' (e.g. \"Authorization: Bearer sk_live_51Nq9abcDEF1234567890ghijklMNO\")"New value: +"Raw log output, .env file, code snippet, or unified git diff to scan."
    • addedInput schema / properties / text / example
      Added value: +"export GITHUB_TOKEN=ghp_1234567890abcdefghijklmnopqrstuvwxyz\nDB_URL=postgres://admin:s3cr3tP@ssw0rd99@db.internal:5432/prod"
    • addedInput schema / properties / text / maxLength
      Added value: +262144
    • addedInput schema / properties / text / minLength
      Added value: +1
    • addedInput schema / properties / types
      Added value: +{
      +  "description": "Optional allowlist of secret types to scan for. Scans all 18 types when omitted.",
      +  "items": {
      +    "enum": [
      +      "OPENAI_API_KEY",
      +      "ANTHROPIC_API_KEY",
      +      "HUGGINGFACE_TOKEN",
      +      "AWS_ACCESS_KEY_ID",
      +      "AWS_SECRET_ACCESS_KEY",
      +      "GITHUB_TOKEN",
      +      "GITLAB_TOKEN",
      +      "SLACK_TOKEN",
      +      "SLACK_WEBHOOK",
      +      "STRIPE_KEY",
      +      "GOOGLE_API_KEY",
      +      "SENDGRID_API_KEY",
      +      "TWILIO_API_KEY",
      +      "MAILGUN_API_KEY",
      +      "SHOPIFY_TOKEN",
      +      "NPM_TOKEN",
      +      "PYPI_TOKEN",
      +      "DATABRICKS_TOKEN",
      +      "DIGITALOCEAN_TOKEN",
      +      "LINEAR_API_KEY",
      +      "SUPABASE_TOKEN",
      +      "POSTMAN_API_KEY",
      +      "DISCORD_WEBHOOK",
      +      "TELEGRAM_BOT_TOKEN",
      +      "PRIVATE_KEY",
      +      "JWT",
      +      "BASIC_AUTH_URL",
      +      "GENERIC_HIGH_ENTROPY"
      +    ],
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "text",
      -  "redact"
      -]New value: +[
      +  "text"
      +]
  4. First observed

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description's added value is the masking semantics and the endpoint path, but it does not state that the original text is recoverable via the restore sibling, nor what the response contains — the caller-only secret map is disclosed only inside the schema's mode enum. Adequate, not rich.

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?

Two short sentences, front-loaded with the action, with the endpoint appended as a compact technical aside. The opening label duplicates the annotation title verbatim, which is mild filler, but nothing else is wasted.

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?

With five parameters, a 256KB input limit, and no output schema, the definition should say what comes back — masked text, a match list, or a token-to-secret map — and that the mapping only exists in token mode. It leaves the return contract and the restore workflow undocumented, which is the main completeness gap for a redaction tool.

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% and every parameter (mode, types, min_entropy, diff_only_added, text) carries its own detailed description and examples. The description adds no parameter meaning beyond the schema, so the baseline 3 applies.

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 gives a specific verb pair ("Detect and mask") plus the resource categories (API keys, JWTs, private keys) and the input surfaces (logs, diffs, prompts), so the tool's job is immediately legible. It does not differentiate itself from the obvious sibling tinplate_secret_scanner_restore, leaving the agent to infer the read/mask vs. restore split from the name alone.

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

Usage Guidelines3/5

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

"in logs, diffs, and prompts" implies the contexts where this tool applies, which is more than nothing. However, there is no explicit when-to-use/when-not guidance and no pointer to the restore sibling or to tinplate_pii_redactor, both of which an agent could plausibly confuse it with.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources