← repo-context-mcp

repo-context-mcp 1.8.0

npm · repo-context-mcp · current release

11
Tools
11
Resources
0
Templates
3
Prompts

Observation

Observed 2026-08-26T10:10:40.991Z using mcpSecurity-inventory. Status: partial. Negotiated protocol: 2025-06-18.

Server capabilities
{
  "tools": {},
  "resources": {},
  "prompts": {}
}

Tools 11

ToolCategoryAnnotationsRisk
annotateAdd/remove/list project annotations (business rules, gotchas, warnings).
Input schema
{
  "type": "object",
  "properties": {
    "action": {
      "type": "string",
      "enum": [
        "list",
        "add",
        "remove"
      ],
      "description": "Action to perform"
    },
    "category": {
      "type": "string",
      "enum": [
        "businessRules",
        "gotchas",
        "warnings"
      ],
      "description": "Category (required for add/remove)"
    },
    "text": {
      "type": "string",
      "description": "Text to add (required for add)"
    },
    "index": {
      "type": "number",
      "description": "Index to remove (required for remove)"
    }
  },
  "required": [
    "action"
  ]
}
—— · ——
generate_project_docsRegenerate .repo-context/ docs. Usually automatic.
Input schema
{
  "type": "object",
  "properties": {},
  "required": []
}
—— · ——
get_diagnosticsRun project diagnostics and return ONLY fatal errors. Auto-detects language (TypeScript, Rust, Go, Python, .NET, Java, Ruby, Swift, PHP) and runs the appropriate checker. Spelling errors and warnings are filtered out to save tokens.
Input schema
{
  "type": "object",
  "properties": {},
  "required": []
}
—— · ——
get_project_contextCall FIRST. Returns project context. Use section param for specific info.
Input schema
{
  "type": "object",
  "properties": {
    "format": {
      "type": "string",
      "enum": [
        "ultra",
        "compact",
        "normal",
        "minimal",
        "json"
      ],
      "description": "Output format (default: compact)"
    },
    "section": {
      "type": "string",
      "enum": [
        "all",
        "stack",
        "structure",
        "endpoints",
        "models",
        "status",
        "hotfiles",
        "modified",
        "imports",
        "annotations"
      ],
      "description": "Specific section (default: all). Use \"modified\" for git-modified files only."
    },
    "force_refresh": {
      "type": "boolean",
      "description": "Force re-analysis"
    }
  },
  "required": []
}
—— · ——
list_filesList files/dirs. Respects .gitignore.
Input schema
{
  "type": "object",
  "properties": {
    "path": {
      "type": "string",
      "description": "Dir path (default: root)"
    },
    "pattern": {
      "type": "string",
      "description": "Glob filter"
    },
    "max_depth": {
      "type": "number",
      "description": "Depth (default: 3)"
    }
  },
  "required": []
}
—— · ——
read_fileSmart reader. <200L: full content. >200L: outline. Optional line range.
Input schema
{
  "type": "object",
  "properties": {
    "file": {
      "type": "string",
      "description": "Relative path to file"
    },
    "start_line": {
      "type": "number",
      "description": "Start line"
    },
    "end_line": {
      "type": "number",
      "description": "End line"
    }
  },
  "required": [
    "file"
  ]
}
—— · ——
read_file_outlineFile outline: symbols with line ranges (~100 tokens). Use depth=1 for top-level only (~80t vs ~450t on complex files).
Input schema
{
  "type": "object",
  "properties": {
    "file": {
      "type": "string",
      "description": "Relative path"
    },
    "depth": {
      "type": "number",
      "description": "Symbol depth: 1 = top-level only (no nested consts/functions). Reduces ~450t to ~80t for complex files."
    }
  },
  "required": [
    "file"
  ]
}
—— · ——
read_file_symbolRead function/class by name. Fuzzy matching supported.
Input schema
{
  "type": "object",
  "properties": {
    "file": {
      "type": "string",
      "description": "Relative path"
    },
    "symbol": {
      "type": "string",
      "description": "Symbol name"
    }
  },
  "required": [
    "file",
    "symbol"
  ]
}
—— · ——
search_in_fileSearch pattern in file. Regex supported.
Input schema
{
  "type": "object",
  "properties": {
    "file": {
      "type": "string",
      "description": "Relative path"
    },
    "pattern": {
      "type": "string",
      "description": "Pattern (string/regex)"
    },
    "context_lines": {
      "type": "number",
      "description": "Context lines (default: 2)"
    },
    "max_matches": {
      "type": "number",
      "description": "Max matches (default: 50)"
    }
  },
  "required": [
    "file",
    "pattern"
  ]
}
—— · ——
search_in_projectSearch across all project files. Default: 1-line compact output — total matches, file count, top 10 hottest files. Use max_files=N for code detail on N files. Use max_files=-1 with file_pattern to get all matching files grouped and sorted (replaces grep).
Input schema
{
  "type": "object",
  "properties": {
    "pattern": {
      "type": "string",
      "description": "Pattern (string/regex)"
    },
    "file_pattern": {
      "type": "string",
      "description": "Glob filter. Supports multi-glob: \"*.ts,*.tsx\" or brace expansion \"*.{ts,tsx}\". With max_files=-1 acts as grep replacement"
    },
    "max_results": {
      "type": "number",
      "description": "Max matches shown per file in detail (default: 30)"
    },
    "context_lines": {
      "type": "number",
      "description": "Context lines around each match (default: 0)"
    },
    "max_files": {
      "type": "number",
      "description": "Files to show code detail for (default: 0 = compact summary only). Use max_files=5 to see code. Use max_files=-1 with file_pattern to show ALL matching files grouped by file, sorted by match count — respects .gitignore, skips binaries."
    },
    "exclude_pattern": {
      "type": "string",
      "description": "Glob pattern to exclude files (e.g. \"*.md\", \"docs/**\"). Comma-separated for multiple patterns."
    }
  },
  "required": [
    "pattern"
  ]
}
—— · ——
search_symbolSearch for a symbol (function, class, interface, type, const, enum) across ALL project files. Returns file location, type, signature, and exported status. Fuzzy matching supported.
Input schema
{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "Symbol name(s) to search for. Comma-separated for multi-search: \"handleDelete,handleEdit\". Supports fuzzy matching."
    },
    "type": {
      "type": "string",
      "description": "Filter by symbol type",
      "enum": [
        "function",
        "class",
        "interface",
        "type",
        "const",
        "enum",
        "method",
        "export"
      ]
    },
    "exported_only": {
      "type": "boolean",
      "description": "Only return exported symbols (default: false)"
    }
  },
  "required": [
    "name"
  ]
}
—— · ——

Resources 11

Resource templates 0

Prompts 3

Let’s talk about MCP security.

Share your details and our security team will contact you.