{
  "data": null,
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/niches/code.understand-codebase/",
    "json": "https://www.anchorterminal.com/niches/code.understand-codebase/index.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/niches/code.understand-codebase/index.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/niches/code.understand-codebase/index.min.md"
  },
  "markdown": "No company's docs show a full fit yet. The listings below do the job with a limit, or not at all.\n\n| Companies, full fit | With a limit | Carry the tag | Share of the category's work | First-hand accounts |\n| --- | --- | --- | --- | --- |\n| 0 | 8 | 25 | 14 | 11 |\n\n## What counts as done\n\nDefinitions, references or the relevant files are named with repository and path, and the answer is checkable against the current revision.\n\nMeasured, for our own tests: the answer comes in one or two calls, and the total tokens returned are lower than a grep of the same question would have cost.\n\nHow agents ask for it: where is this function used across our repos; give me an overview of this repository; find the code that handles X; what calls this before I change it\n\n## Does the job, with a limit\n\nIt does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.\n\n- **Azure DevOps MCP Server (Microsoft Corporation)**: search_code is full-text search across the organisation and repo_file reads files; no definitions or references, and one account saw a project listing fill 160,000 tokens of context.\n- **Entire (Entire Inc)**: The entire-graph plugin's graph query ranks source regions within a 24,576-byte budget and graph impact lists callers and callees with file and line; one repository per --repo, the plugin must be installed first, and the token saving is Entire's own figure.\n- **GitHub MCP Server (GitHub, Inc.)**: search_code searches across every repository the token reaches and get_file_contents takes fields and ref; no definitions or references, and the token cost of the schema is 4 to 32 times a gh call.\n- **GitLab MCP Server (GitLab Inc.)**: search and semantic_search run across projects and get_repository_file caps at 2,000 lines; one account relies on it for cross-repository reads, but there are no definitions or references.\n- **GitMCP (Ido Salomon (GitMCP open-source project))**: search_\u003crepo\u003e_code uses GitHub code search within one public repository and one account saved hours browsing MLflow with it; one repository per URL, no private code, no definitions or references.\n- **graft (Vishisht Choudhary (individual))**: /v1/grep, /v1/search and /v1/log run server-side without a clone and take limit and path; one repository per server, no definitions or references, and a project first committed on 13 October 2026.\n- **Graphify (Graphify Labs)**: query_graph, get_neighbors, shortest_path and god_nodes answer within a 2,000-token default budget, with CLI and skill routes for 24 assistants; but one benchmark saw 5 per cent more tokens, large-repo queries were slow, and agents fall back to grep.\n- **Sourcegraph MCP Server (Sourcegraph, Inc.)**: keyword_search and nls_search span the instance, go_to_definition and find_references give compiler-accurate results, read_file takes startLine and endLine; two accounts report better results and fewer tokens; but Enterprise only from $16,000 a year, and code_finder and deepsearch error when their quota is spent.\n\n- not this job: amCharts 5 MCP Server (amCharts): Serves vendor documentation, not the user's repositories.\n- not this job: Context7 (Upstash): Indexes documentation, including private sources on Pro, not code search over a repository.\n- not this job: Git (MCP reference server) (Model Context Protocol, a Series of LF Projects, LLC): git_log, git_show and git_branch read one local repository; no search or navigation.\n- not this job: Jam MCP (Jam): No code tools.\n- not this job: Microsoft Learn MCP Server (Microsoft Corporation): Microsoft documentation only; no repository tools.\n- not this job: ModusToolbox AI Assistant (Infineon Technologies AG): Analyses a ModusToolbox workspace for device context; not a code search tool.\n- not this job: Momentic MCP server (Momentic): No code tools.\n- not this job: REA (morluto): Analyses compiled binaries, Electron apps and websites without source; it does not search a source repository.\n- not this job: Ref (Ref Software, Inc): Indexes documentation and PDFs; not a code search tool.\n- not this job: Salesforce DX MCP Server (Salesforce, Inc.): No code search tools.\n- not this job: Superpowers (Prime Radiant (no legal form or registration found on its pages); the MIT LICENSE names Jesse Vincent): No code search or graph.\n- not this job: TokenEconomizer (Microsoft Corporation (repository in the microsoft GitHub organisation with Microsoft's SECURITY.md); co-authors at UC Berkeley): Injects learned facts about a repository; it does not search or map code.\n- not this job: Void (Cloudflare, Inc. (VoidZero)): No code search.\n\n## What stops agents finishing\n\n- Enterprise plan from a $16,000 annual minimum (Sourcegraph)\n- code_finder and Deep Search draw on a credit quota and error when it is spent\n- graph build of 15 to 26 minutes on a large repo before the first query\n- agents ignore the graph tool and fall back to grep unless the harness forces it\n\n## Around it\n\nBefore: code.host-ops. After: code.ticket-to-pr, code.review-pr.\n\n## Where this comes from\n\nWeight 14 of 100 in Code \u0026 developer platforms: 11 of 65 accounts (Sourcegraph 2, GitLab cross-repo 1, Graphify 4, DeepWiki 3, GitMCP code search 1); several measure token use, which is why users adopt or drop these tools\n\nAs data: https://www.anchorterminal.com/api/v1/use-cases/code.understand-codebase.json, or the MCP tool get_use_case with id code.understand-codebase. Draft, read 2026-11-12 from public docs and first-hand accounts, not yet reviewed by a person.\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "For agents",
        "url": "https://www.anchorterminal.com/agents/"
      },
      {
        "name": "Niches",
        "url": "https://www.anchorterminal.com/niches/"
      },
      {
        "name": "Map or search a large or unfamiliar codebase",
        "url": ""
      }
    ],
    "description": "Map or search a large or unfamiliar codebase: 0 companies fully do it, 8 with a limit, 25 carry the tag. Every listing in Code \u0026 developer platforms with the reason and a source.",
    "facts": null,
    "h1": "Map or search a large or unfamiliar codebase",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/niches/code.understand-codebase/",
    "published": "",
    "section": "agents",
    "title": "Map or search a large or unfamiliar codebase | Anchor Terminal",
    "toc": null,
    "updated": "2026-11-15",
    "url": "https://www.anchorterminal.com/niches/code.understand-codebase/"
  },
  "tokens": {
    "markdown": 1550,
    "slim": 280
  },
  "version": 1
}
