Server data from the Official MCP Registry
Extracts decision intent from git history and protects intentional code from AI modification.
Extracts decision intent from git history and protects intentional code from AI modification.
Valid MCP server (2 strong, 3 medium validity signals). 1 code issue detected. No known CVEs in dependencies. Package registry verified. Imported from the Official MCP Registry. Trust signals: 4 highly-trusted packages.
4 files analyzed · 2 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-sandip124-wisegit": {
"args": [
"-y",
"@sandip124/wisegit"
],
"command": "npx"
}
}
}From the project's GitHub README.
"Don't take a fence down until you know the reason it was put up." — G.K. Chesterton
wisegit is a local MCP server that extracts decision intent from git history and protects intentional code from AI modification.
When Claude Code (or any MCP-compatible agent) is about to edit a file, wisegit injects a decision manifest showing which functions are frozen, stable, or open — so the AI respects what was intentional, not just what compiles.
Zero config. Zero external services. Everything local.
# Set up any repo (one command)
npx @sandip124/wisegit setup
# Or add as MCP server globally
claude mcp add wisegit -- npx @sandip124/wisegit serve
LLMs have no concept of intentional code. A manually-tested fix and a broken stub look identical — both are just text. Real scenario:
sleep(350) — manually tested, committed.sleep(350) — looks like dead code.Root cause: git history contains proof of intention. Nobody extracts it.
Git History → Tree-sitter AST → Intent Extraction → SQLite Event Store → MCP Tools
fix:, feat:), DESCRIPTIVE (plain sentences), or NOISE (wip, x)get_file_decisions before editing any file[DECISION MANIFEST: payment.service.cs]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
FROZEN: ProcessPayment() [score: 0.89] [Recovery: L1]
- sleep(350) → Stripe race condition. Won't Fix.
HIGH — commit a3f19b2
STABLE: ValidateOrder() [score: 0.55] [Recovery: L2]
- Fixed null reference on Safari iOS WebKit.
MEDIUM — commit 7c14694
OPEN: FormatReceipt() [score: 0.12] [Recovery: L3]
← safe to modify
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
That's it. No Docker, no PostgreSQL, no external services.
cd /path/to/your/repo
npx @sandip124/wisegit setup
This single command:
~/.wisegit/wisegit.db.mcp.json for Claude Code auto-discoveryCLAUDE.md rules that instruct AI to check before editing.mcp.json to .gitignore# Fetch issue/PR details from GitHub/GitLab
GITHUB_TOKEN=ghp_... npx @sandip124/wisegit enrich
This fetches referenced issues (e.g., #134 in commit messages), detects Won't Fix / By Design decisions, and boosts freeze scores for functions linked to those issues.
Open the repo in Claude Code. It will automatically:
.mcp.json)CLAUDE.md)get_file_decisions before editing any file| Tool | Description |
|---|---|
get_file_decisions | Decision manifest for a file — freeze scores, intent history, recovery levels, override status |
get_freeze_score | Score + signal breakdown for a specific function |
get_function_history | Full chronological decision timeline for a function |
get_theory_gaps | Functions with unrecoverable rationale (inactive authors, timeline gaps) |
get_branch_context | Branch merge history — what was migrated and why |
search_decisions | Search past decisions by keyword across the entire repo |
create_override | Override a frozen function (user approves in Claude Code UI) |
extract_intent | Extract intent for NOISE commits using the host LLM — no Ollama needed |
find_similar_functions | Search for existing functions that solve a similar problem before writing new code |
predict_impact | Predict what functions will break if a given function is modified |
get_codebase_conventions | Extract coding conventions for a file's neighborhood |
MCP Resource: wisegit://manifest/{filePath} — decision manifest as auto-discoverable resource
MCP Prompt: check_before_edit — mandatory workflow prompt that returns the decision manifest before editing any file
wisegit uses a smart fallback chain for extracting intent from NOISE commits:
| Context | LLM Used | How |
|---|---|---|
| Inside Claude Code | Host LLM (Claude) | MCP sampling — asks Claude to analyze the diff. Zero setup. |
| CLI with Ollama | Ollama (llama3) | wisegit init --ollama — uses local Ollama instance |
| CLI without Ollama | None | Rule-based extraction only, NOISE commits get no intent |
Inside Claude Code, call extract_intent to retroactively recover intent for NOISE commits — uses Claude itself, no Ollama installation needed.
wisegit setup [--path <dir>] [--global] # One-command repo setup
wisegit init [--full-history] [--path <dir>] # Index git history
wisegit enrich [--path <dir>] # Fetch issue/PR context from GitHub/GitLab
wisegit audit <file> # Show decision manifest
wisegit history <target> [--file <path>] # Show decision timeline
wisegit recompute [--path <dir>] # Recompute scores with PageRank + theory gaps
wisegit override <fn> --file <f> --reason "..." # Override a frozen function
wisegit overrides # List active overrides
wisegit sync # Rebuild local cache from git + .wisegit/
wisegit config list # View team configuration
wisegit config set <key> <value> # Modify team policy
wisegit team-status # Team overview: enrichments, overrides, contributors
wisegit team-health # Theory health: healthy/fragile/critical functions
wisegit branch-capture # Capture branch context from last merge
wisegit branch-list # List all captured branch snapshots
wisegit branch-recover <sha> # Recover context from old merge commit
wisegit calibrate # Show adaptive obsolescence weights vs defaults
wisegit report [--output <file>] # Generate HTML report with scores + insights
wisegit serve # Start MCP server (stdio)
wisegit hook install|uninstall # Manage git hooks (post-commit + post-merge)
Run npx @sandip124/wisegit setup in any repo. It creates .mcp.json automatically.
claude mcp add wisegit -- npx @sandip124/wisegit serve
.mcp.jsonCreate .mcp.json in your repo root:
{
"wisegit": {
"command": "npx",
"args": ["@sandip124/wisegit", "serve"]
}
}
| Language | Extensions |
|---|---|
| C# | .cs |
| TypeScript | .ts, .tsx |
| JavaScript | .js, .jsx, .mjs, .cjs |
| Python | .py |
| Go | .go |
| Rust | .rs |
More languages can be added via Tree-sitter grammar configs in src/ast/languages/.
A commit saying fix: handle null token #134 points to an issue containing reproduction steps, root cause, and explicit decision rationale — everything the commit message never says.
# Fetch issue context from GitHub/GitLab
wisegit enrich --path /path/to/repo
# With auth (5000 req/hr instead of 60)
GITHUB_TOKEN=ghp_... wisegit enrich
Supported platforms: GitHub, GitLab (Azure DevOps, Jira, Bitbucket planned)
Auth tokens: GITHUB_TOKEN / GH_TOKEN for GitHub, GITLAB_TOKEN for GitLab. Never stored by wisegit.
| Signal | Freeze Boost | When |
|---|---|---|
| Won't Fix / By Design | +0.35 | Issue closed as not_planned, or has wontfix/by-design label, or comment says "intentional" |
| Reproduction steps | +0.15 | Issue body contains "steps to reproduce" |
| Platform-specific label | +0.10 | Issue labeled ios, safari, windows, etc. |
| Issue unreachable | +0.10 | Issue ref exists but API returned 404 — absent context = protect more |
| PR review comments | +0.15 | Linked PR had reviewer discussion |
The freeze score is never stored directly — it's derived by replaying the event stream for each function. Signal categories:
| Category | Weight | Source |
|---|---|---|
| Git History | 0.20 | Reverts, verified keywords, incident refs, contributor count, Weibull age [18] |
| Issue Enrichment | 0.20 | Won't Fix/By Design, reproduction steps, platform labels |
| Code Structure | 0.15 | Inline comments, magic numbers, defensive patterns |
| Test Signals | 0.15 | Dedicated tests, edge case labels, co-committed tests |
| Structural Importance | 0.15 | Call count (PageRank), public API, DOE expertise model [19] |
| Naur Theory | 0.10 | Global patterns, intentional contradictions, removal cost |
| Aranda Signals | 0.05 | Forgotten patterns, timeline gaps, broken issue links |
| Obsolescence (8 signals) | adaptive | Dead code, stale subgraph, migration leftover, obsolete deps, superseded, SAAD, change burst absence, co-change divergence |
Freeze score formula:
freeze_score = base_score x (1 - obsolescence_penalty)
Protection signals produce the base score (weighted average of present signal categories, not additive sum); obsolescence signals produce the penalty. Obsolescence weights are adaptive — calibrated per-repository using Shannon entropy and Bayesian feedback. Falls back to hardcoded defaults when < 20 functions have signals. Age signal uses Weibull survival model [18] (k=0.7, lambda=2.4y); contributor expertise uses DOE model [19] (4 variables: contribution share, recency, duration, frequency).
Academic grounding: 24 published papers. See REFERENCE.md for full citations.
Tested on 3 real-world open-source codebases:
| Repo | Commits | Functions | FROZEN | STABLE | Max Score |
|---|---|---|---|---|---|
| pallets/flask | 5,565 | 4,355 | 72 | 2,272 | 0.927 |
| expressjs/express | 6,382 | 409 | 1 | 247 | 0.811 |
| zeeguu/api | 4,515 | 3,216 | 1 | 12 | 0.583 |
Flask's core APIs (__init__, run, wsgi_app, url_for) correctly scored FROZEN (0.87+). Express routing primitives (paramCallback, Route, Router) correctly scored FROZEN/STABLE. Scores adapt to each codebase's history rather than producing uniform distributions.
See REFERENCE.md for detailed validation findings and implementation changes.
wisegit is designed for codebases that have accumulated years of intentional decisions. The freeze score doesn't mean "never change this" — it means "understand these decisions before you change it."
Progressive migration, not shiny rewrites. Per Távora [12]: the business rules in messy code are correct and valuable. The technical debt is in the structure, not the decisions. wisegit protects the decisions while you fix the structure.
| Stage | How wisegit helps |
|---|---|
| Understand AS-IS | wisegit audit shows what's intentional. wisegit team-health shows where institutional knowledge is lost. |
| Protect during refactoring | Manifests tell developers + AI which behaviors were deliberately chosen |
| Record rationale | Override reasons persist in .wisegit/overrides.jsonl — not buried in Slack |
| Preserve migration context | Branch snapshots record what was replaced and what should never return |
| Track cross-boundary deps | Co-change signals detect coupling between legacy and replacement code |
See REFERENCE.md for the full legacy evolution section with academic grounding (24 published papers).
wisegit uses a three-layer architecture — no separate "team mode" needed:
| Layer | What | Shared? |
|---|---|---|
| Deterministic base | Commit classification, rule-based intent, git signals | Via git (automatic) |
| Team knowledge | Enrichments, overrides, intents, branch contexts | Via .wisegit/ (git-tracked) |
| Local cache | SQLite at ~/.wisegit/wisegit.db | Never (derived) |
.wisegit/ # Tracked by git — shared with team
├── config.json # Team policy (thresholds, AI authors)
├── enrichments.jsonl # Issue enrichment cache
├── overrides.jsonl # Override audit trail
└── branch-contexts.jsonl # Branch merge snapshots
JSONL format — one JSON object per line. Concurrent appends produce no git merge conflicts.
After a teammate pushes .wisegit/ changes, run wisegit sync to import them into your local cache.
See TEAM-ROADMAP.md for the full team architecture design.
┌─────────────────────────────────────────────────┐
│ Claude Code / MCP Client │
│ ┌───────────────────────────────────────────┐ │
│ │ 1. Reads CLAUDE.md protection rules │ │
│ │ 2. Calls get_file_decisions before edits │ │
│ │ 3. Respects FROZEN / STABLE / OPEN │ │
│ └───────────────────────────────────────────┘ │
└─────────────────┬───────────────────────────────┘
│ MCP (stdio)
┌─────────────────▼───────────────────────────────┐
│ wisegit MCP Server │
│ ┌──────────┐ ┌──────────┐ ┌─────────────────┐ │
│ │get_file_ │ │get_freeze│ │search_decisions │ │
│ │decisions │ │_score │ │ │ │
│ └────┬─────┘ └────┬─────┘ └───────┬─────────┘ │
└───────┼─────────────┼───────────────┼───────────┘
│ │ │
┌───────▼─────────────▼───────────────▼───────────┐
│ SQLite (~/.wisegit/wisegit.db) │
│ ┌──────────────┐ ┌────────────┐ ┌───────────┐ │
│ │decision_events│ │freeze_scores│ │issue_ │ │
│ │(append-only) │ │(derived) │ │enrichments│ │
│ └──────────────┘ └────────────┘ └─────┬─────┘ │
└────────────────────────────────────────┼────────┘
│
┌────────────────────────────────────────▼────────┐
│ Issue Enrichment (wisegit enrich) │
│ ┌─────────┐ ┌─────────┐ ┌──────────────────┐ │
│ │ GitHub │ │ GitLab │ │ Jira (planned) │ │
│ │ REST API│ │ REST API│ │ │ │
│ └─────────┘ └─────────┘ └──────────────────┘ │
└─────────────────────────────────────────────────┘
| Variable | Default | Description |
|---|---|---|
WISEGIT_DB_PATH | ~/.wisegit/wisegit.db | SQLite database path |
GITHUB_TOKEN / GH_TOKEN | — | GitHub API token (5000 req/hr vs 60 unauthenticated) |
GITLAB_TOKEN | — | GitLab API token for issue enrichment |
OLLAMA_URL | http://localhost:11434 | Ollama server URL (Phase 2) |
OLLAMA_CHAT_MODEL | llama3 | Model for intent extraction (Phase 2) |
OLLAMA_EMBED_MODEL | nomic-embed-text | Model for embeddings (Phase 2) |
wisegit enrich)~/.wisegit/wisegit.db — no network exposure.wisegit/ directory with JSONL files for enrichments, overrides, branch contexts, and team configwisegit calibrate CLIMIT
Be 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.
by Microsoft · Content & Media
Convert files (PDF, Word, Excel, images, audio) to Markdown for LLM consumption
by mcp-marketplace · Developer Tools
Scaffold, build, and publish TypeScript MCP servers to npm — conversationally
by mcp-marketplace · Finance
Free stock data and market news for any MCP-compatible AI assistant.