Server definition

Hash: sha256:3d97db5f7893b88fe3d9307c9f0ce1900d612bdeb666931271ae95f1599c3241
What it is: What a remote MCP server returned when asked what it offers: 7 tools

The blob, as servednamed by its sha256

{
  "instructions": "Moltline Code Review & AI-Code Verifier: review diffs and files the way a skeptical senior engineer would. Free: review_diff (risk-scan a unified diff), ai_code_smell_scan (flag AI-generated-code tells), complexity_report, secret_scan, review_checklist. Premium (license): security_deep_dive, get_reviewer_persona. Every finding cites the line and says why it matters.",
  "tools": [
    {
      "description": "Flag the tells of unreviewed AI-generated code in a source file. FREE.\n\nDetects comments that restate the next line, leaked assistant preambles,\nplaceholder TODOs, shipped 'Example usage' blocks, over-broad try/except\nthat swallows errors, and auto-named identifiers. Typical input\n{\"code\": \"<file contents>\"} returns {\"reviewed_confidence\": 0-100,\n\"hits\": [{\"smell\": \"...\", \"evidence\": \"<quoted snippet>\"}], \"reading\":\n\"...\", \"note\": \"...\"}.\n\nUse on a full source file suspected of unreviewed machine authorship. Not\non a diff (review_diff), and the result is a signal to check, not proof of\nauthorship. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {\"error\": \"<what is wrong and how to fix it>\"}. Every call is read-only and idempotent, so after correcting the input it is always safe to retry.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "code": {
            "description": "Full source text to scan, any language; paste the file\ncontents as a single string.",
            "type": "string"
          }
        },
        "required": [
          "code"
        ],
        "type": "object"
      },
      "name": "ai_code_smell_scan",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Report structural complexity of a source file, function by function. FREE.\n\nMeasures per-function length, max nesting depth, and a cyclomatic-style\nbranch count (if/for/while/case/&&/||/except), flagging functions too\nlong or too deeply nested to review confidently. Typical input\n{\"code\": \"<file contents>\"} returns {\"functions\": N, \"detail\":\n[{\"name\": ..., \"start\": N, \"lines\": N, \"branches\": N, \"max_depth\": N}],\n\"flags\": [\"...\"], \"note\": \"...\"}.\n\nUse when structure rather than correctness is the question. Not for\nvulnerabilities (security_deep_dive). Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {\"error\": \"<what is wrong and how to fix it>\"}. Every call is read-only and idempotent, so after correcting the input it is always safe to retry.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "code": {
            "description": "Full source text to analyze, pasted as a single string.",
            "type": "string"
          },
          "language": {
            "default": "auto",
            "description": "Optional language hint, e.g. \"python\" or \"javascript\";\n\"auto\" (default) detects from syntax.",
            "type": "string"
          }
        },
        "required": [
          "code"
        ],
        "type": "object"
      },
      "name": "complexity_report",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Load the Senior Reviewer persona for consistent, high-signal reviews. PREMIUM (license).\n\nThe persona is a reviewing voice that is skeptical, specific, and kind —\ndemands evidence over vibes and blocks only on real risk. Takes no\narguments. Returns {\"persona\": ..., \"identity\": ..., \"rules\": [\"...\",\n...], \"opening_move\": \"...\"} ready to adopt as a system prompt.\n\nUse to keep repeated reviews consistent in voice and rigor. Not for\nrunning a review - the scan tools do that. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {\"error\": \"<what is wrong and how to fix it>\"}. Every call is read-only and idempotent, so after correcting the input it is always safe to retry.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {},
        "type": "object"
      },
      "name": "get_reviewer_persona",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Produce a focused pull-request review checklist for a language or stack. FREE.\n\nCovers the things that actually break in production, with extra items per\nlanguage. Typical input {\"language\": \"python\"} returns {\"language\":\n\"python\", \"checklist\": [\"...\", ...], \"note\": \"...\"}.\n\nUse before a review, to decide what to look for. Not for reviewing actual\ncode - pass code to review_diff or security_deep_dive. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {\"error\": \"<what is wrong and how to fix it>\"}. Every call is read-only and idempotent, so after correcting the input it is always safe to retry.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "language": {
            "default": "general",
            "description": "Language or stack to tailor for: \"python\", \"javascript\",\n\"typescript\", \"go\", \"sql\", or \"general\" (default). Unknown values\nfall back to the general checklist.",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "review_checklist",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Risk-scan a unified diff the way a senior reviewer triages a PR. FREE.\n\nFlags added lines matching known risk patterns — injection sinks, disabled\nTLS, bare excepts, debug prints, TODOs, N+1 hints, leaked secrets — with\nthe new-file line number and a severity (1 low - 4 high). Typical input\n{\"diff\": \"<git diff output>\"} returns {\"added_lines\": N, \"risk_score\":\n0-100, \"verdict\": \"...\", \"secrets\": [...], \"findings\": [{\"line\": N,\n\"severity\": 1-4, \"issue\": \"...\", \"code\": \"...\"}], \"note\": \"...\"}.\n\nUse on a unified diff, when only the change matters. Not for whole-file\nanalysis (complexity_report, ai_code_smell_scan). Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {\"error\": \"<what is wrong and how to fix it>\"}. Every call is read-only and idempotent, so after correcting the input it is always safe to retry.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "diff": {
            "description": "A unified diff exactly as produced by `git diff` — text with\n@@ hunk headers and +/- line prefixes. Only added (+) lines are\nscanned.",
            "type": "string"
          }
        },
        "required": [
          "diff"
        ],
        "type": "object"
      },
      "name": "review_diff",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Scan text for accidentally-committed machine credentials and private-key material. FREE.\n\nReports each match's location and category so it can be rotated before it\nleaks. Detection is pattern-based over the common leaked-credential\nformats; it never echoes the matched value back. Typical input\n{\"text\": \"<file, diff, or config contents>\"} returns {\"leaked\": bool,\n\"count\": N, \"findings\": [{\"line\": N, \"type\": \"<category>\"}], \"note\": \"...\"}.\n\nPattern matching only - a clean result is not proof, and every hit needs\nhuman confirmation before anyone acts on it. Not a general security review\n(security_deep_dive). Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {\"error\": \"<what is wrong and how to fix it>\"}. Every call is read-only and idempotent, so after correcting the input it is always safe to retry.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "text": {
            "description": "The file, diff, or config contents to scan, pasted as a\nsingle string.",
            "type": "string"
          }
        },
        "required": [
          "text"
        ],
        "type": "object"
      },
      "name": "secret_scan",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    },
    {
      "description": "Run an OWASP-oriented security pass over a source file. PREMIUM (license).\n\nChecks injection sinks, auth/session handling, crypto misuse,\nSSRF/deserialization, and unsafe file/path handling — each finding cites\nthe line, the OWASP risk class, and a concrete fix direction. Typical\ninput {\"code\": \"<file contents>\"} returns {\"issues\": N, \"findings\":\n[{\"line\": N, \"class\": \"A03 Injection\", \"fix\": \"...\", \"code\": \"...\"}],\n\"owasp_note\": \"...\"}.\n\nUse on one source file when vulnerabilities are the question. Not for\nstyle or structure (complexity_report), and never a substitute for a\nsecurity professional on high-risk code. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {\"error\": \"<what is wrong and how to fix it>\"}. Every call is read-only and idempotent, so after correcting the input it is always safe to retry.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "code": {
            "description": "Full source text to audit, pasted as a single string; any\ncommon language.",
            "type": "string"
          }
        },
        "required": [
          "code"
        ],
        "type": "object"
      },
      "name": "security_deep_dive",
      "outputSchema": {
        "additionalProperties": true,
        "type": "object"
      }
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:3d97db5f7893b88fe3d9307c9f0ce1900d612bdeb666931271ae95f1599c3241 | sha256sum