Server data from the Official MCP Registry
Architecture-aware MCP context with boundaries, seams, impact scope, and BGI-TWIN guidance.
Architecture-aware MCP context with boundaries, seams, impact scope, and BGI-TWIN guidance.
BGI is a static code analysis tool with well-structured MCP integration and reasonable security posture. The codebase demonstrates good input validation, safe file I/O with path traversal guards, and appropriate use of caching and lazy loading. No malicious patterns, hardcoded credentials, or dangerous operations detected. Minor code quality observations around exception handling and logging do not materially affect security. Supply chain analysis found 7 known vulnerabilities in dependencies (0 critical, 4 high severity). Package verification found 1 issue.
4 files analyzed · 11 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Add this to your MCP configuration file:
{
"mcpServers": {
"io-github-ahmedxuhri-bigindexer": {
"args": [
"-y",
"bigindexer-website"
],
"command": "npx"
}
}
}From the project's GitHub README.
Copyright (c) 2026 Ahmed Xuhri — Licensed under Apache-2.0.
BGI is a static architecture analysis tool for large codebases.
It groups code units by behavioral role and emits explicit architectural boundaries.
Project domain: bigindexer.com
Big Indexer is published in the MCP Registry as io.github.ahmedxuhri/bigindexer.
pip install bigindexer==0.1.2
bgi mcp --graph bgi-graph.json --fuse-graph fuse-graph.json
Validation: https://bigindexer.com/validation
Most architecture graphs fail at scale in two ways:
BGI is built to keep both under control, so the output remains usable on large repos.
bgi-graph.json, fuse-graph.json) for automation and review.task_fingerprint, behavioral_twins, twin_context) so they start from proven in-repo patterns.Run BGI on the included fixture repo:
git clone https://github.com/ahmedxuhri/bigindexer
cd bigindexer
pip install -e .
bgi scan tests/fixtures --lang python --out /tmp/bgi-example.json
head -50 /tmp/bgi-example.json
Observed result on this repository:
121426 unitsOne produced edge looks like:
{
"source": "auth_module.py::AuthService::__init__",
"target": "auth_module.py::AuthService::__del__",
"key": "COV.INIT",
"lock": "COV.TEARDOWN",
"type": "HARD"
}
Why this matters: instead of raw syntax references only, you get behavioral relationships plus cluster structure that can drive architecture decisions.
| BGI term | Plain meaning |
|---|---|
| COV token | A behavior label for a unit (for example: FETCH, PERSIST, AUTHENTICATE) |
| Key-Lock edge | A behavioral connection between two units with complementary roles |
| DRS cluster | A group of units likely belonging to one architectural component |
| Fuse edge / fuse event | A refused merge because cluster growth hit the cap; treated as boundary signal |
| Spectral masks | Scope rules that limit where matching is allowed (global, directory, file) |
Source files
->
Gate 1: fingerprint unit behavior (COV tokens)
->
Gate 2: create behavioral edges with scoped matching
->
Gate 3: cluster with hard size cap + boundary emission
->
Artifacts: bgi-graph.json, fuse-graph.json, optional routes/graphml/html
Core approach:
.scm - single-pass query extraction path in Gate 1.| Capability | LSP / SCIP index | Call-graph + generic community detection | BGI |
|---|---|---|---|
| Fast symbol lookup | Strong | Medium | Available (Phase 6 index) |
| Behavioral token model | No | Usually no | Yes |
| Hard-bounded clustering | No | Usually no | Yes |
| First-class boundary artifact | No | Usually no | Yes (fuse-graph.json) |
| Scope-constrained edge generation | Limited | Rare | Yes (spectral masks) |
Comparable kubernetes sample (go comparable mode, 162,917 units):
141.964s67.261s (historical comparable baseline: 138.869s)9.359s218.584s1.113%0Artifact: output/validation/kubernetes-optionb-controlled-median-v21.json
tests/test_gate2.py).tests/test_gate3.py).python3 -m pytest tests/ -x -q (project baseline target remains passing).task → COV → top-3 twins + seam + rubric) is complete: actionability 4.75/5 (p04 slice: 4.8/5), boundary 1.0, hallucinations 0.django/p02 miss.BGI does not treat all languages equally; support is tiered:
.scm): python, typescriptjavascript, java, go, rust, ruby, csharp, php, kotlin, c, scala, lua, elixirswift, r, dart, bash, nim, zig, haskell, ocaml, fsharp, clojure, erlang, matlab, vb, crystal, cobol, groovyUse this as a reliability signal: query-backed and dedicated scanner tiers are stronger than generic fallback.
pip install -e .
# scan
bgi scan /path/to/repo --lang auto --out bgi-graph.json
# optional outputs
bgi scan /path/to/repo --lang auto \
--fuse-graph fuse-graph.json \
--routes routes.json \
--graphml graph.graphml \
--html
# incremental
bgi scan /path/to/repo --lang auto --incremental --cache .bgi-cache.json
# diff
bgi diff /path/before /path/after --lang auto --out diff.json
# run MCP server over generated artifacts
bgi mcp --graph bgi-graph.json --fuse-graph fuse-graph.json
Example MCP usage pattern (from your client prompt):
Use MCP tool twin_context for:
"Add endpoint that validates input and persists data."
Return top twin candidate, seam suggestion, and rubric checklist.
MEMORANDUM.md - design contracts and invariantsdocs/LANGUAGE_SUPPORT.md - language implementation detailsdocs/CONTRIBUTING_LANGUAGES.md - language contribution guidedocs/INDEX_SCHEMA.md - interactive index schemadocs/QUERY_PLANNER.md - query planner scoringdocs/MCP_SETUP.md - MCP server setup and usagehttps://bigindexer.com/validation - public validation evidencedocs/MCP_QUICKSTART_DEMO.md - 5-minute demo walkthroughdocs/MCP_EXAMPLE_TRANSCRIPTS.md - real-world MCP tool invocation examplesdocs/MCP_REAL_TRANSCRIPT.md - unedited transcript from FastAPI analysisscripts/mcp-demo.sh - automated demo script for multiple CLIs and repositoriesLICENSE)DCO) enforced on pull requestsBe the first to review this server!
by Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
by mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.