Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Architecture Drift MCP check if API docs match current implementation"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
English | 한국어
Compare evidence-linked documentation claims with facts observed in the current source tree. The server keeps extraction, deterministic comparison, model adjudication, and patch proposals separate so an uncited guess cannot become confirmed architecture drift.
flowchart LR
A[Discover bounded sources] --> B[Cited documentation claims]
A --> C[Cited implementation facts]
B --> D[Deterministic comparison]
C --> D
D --> E{Evidence strength}
E --> F[Aligned]
E --> G[Suspected or unknown]
E --> H[Evidence-bound adjudication]
H --> I[Review-only patch proposal]Bounded inventory of documentation, manifests, configuration, specifications, and source files
Deterministic command, environment, endpoint, dependency, and service extraction
Host-model claim extraction with exact path and line-range validation
Fresh source hashes that reject mixed old/new citations
Exact semantic alignment plus conservative suspected and unknown states
Confirmed model adjudication restricted to known claim and fact IDs
Review-only documentation replacements that never write into the audited project
Redacted Markdown and JSON reports outside the project tree
Related MCP server: Verinoda
uv tool install "git+https://github.com/efficjump/architecture-drift-mcp.git"
architecture-drift-mcp --transport stdioFor source development:
git clone https://github.com/efficjump/architecture-drift-mcp.git
cd architecture-drift-mcp
uv sync --all-extras --locked
uv run architecture-drift-mcp --transport stdio{
"mcpServers": {
"architecture-drift": {
"command": "architecture-drift-mcp",
"args": ["--transport", "stdio"]
}
}
}The installed command keeps local checkout paths out of client configuration.
Stage | Tools |
Audit state |
|
Discovery |
|
Evidence |
|
Decision |
|
Output |
|
Deterministic absence never becomes confirmed drift. A confirmed adjudication requires known
implementation fact IDs, while unsupported extractor coverage remains unknown.
Project roots must remain inside ARCH_DRIFT_ALLOWED_ROOTS.
Symlinks, binary files, and over-limit sources are excluded from extraction.
Sources are hash-checked again before citation or fact extraction.
Sampled content is redacted and every returned citation is validated against source lines.
Patch proposals are persisted externally and never applied by this server.
The path boundary is not an operating-system sandbox. Audit untrusted projects in isolation.
architecture-drift-mcp --transport streamable-http --host 127.0.0.1 --port 8768The default endpoint is http://127.0.0.1:8768/mcp.
uv sync --all-extras --locked
uv run ruff format --check .
uv run ruff check .
uv run mypy src
uv run pytest --cov --cov-report=term-missing
uv buildSee architecture, security policy, and contribution guide.
Ask the host model to adjudicate drift using only cited, known claim and fact IDs.
Inputs: audit_id (required). Returns: object
Write a redacted Markdown and JSON report in the external audit state directory.
Inputs: audit_id (required). Returns: object
Compare normalized claims and facts; absence remains suspected or unknown.
Inputs: audit_id (required). Returns: object
Create a bounded audit and persist its redacted architecture objective.
Inputs: name (required), objective (required), project_root (required). Returns: object
Refresh the bounded project inventory and invalidate derived stale records.
Inputs: audit_id (required). Returns: object
Extract claims and reject every host claim without a valid line citation.
Inputs: audit_id (required), use_sampling (required), selected_paths (required). Returns: object
Extract current implementation facts from discovered non-documentation files.
Inputs: audit_id (required). Returns: object
Return the current source, claim, fact, comparison, and proposal snapshot.
Inputs: audit_id (required). Returns: object
List persisted audits without reading their project trees.
Inputs: no named parameters. Returns: result
Generate cited review-only document replacements without writing project files.
Inputs: audit_id (required). Returns: object
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 10 tools
Each tool has a clearly distinct responsibility, from audit lifecycle (create/list/get) to the analysis pipeline (discover/extract/compare/adjudicate) to output generation (propose/build). No two tools appear to perform overlapping actions, making misselection unlikely.
All tool names follow a consistent verb_noun pattern using snake_case, with specific verbs like create, list, get, discover, extract, compare, adjudicate, propose, and build. There is no mixing of conventions or ambiguous verbs.
Ten tools is within the optimal range for a specialized workflow. Each tool contributes a unique step in the architecture drift detection process without redundancy or unnecessary bloat.
The tool set covers the full drift detection workflow: audit creation, source discovery, claim/fact extraction, comparison, adjudication, patch proposal, and report generation. Minor gaps exist such as no explicit audit deletion or patch application, but these are not core to the domain.
Find publisher documentation via llms.txt, with source links, evidence and check dates.
Compare engine claims, inspect dissent and check study evidence for student questions.
Search and compare public hosting-provider facts with sources and explicit unknowns.
Read current software facts with primary-source evidence and verification timestamps.