arch-drawing-analyzer
Enables Claude to read and analyze large architectural drawing PDFs by slicing them into manageable chunks and bridging them into Claude's environment via the Filesystem connector.
Warning. Serious findings were identified. Review the full report before connecting. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
ViditJain123
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
get_analysis_promptReturns the analysis prompt template that describes how to analyze each architectural drawing page. Call this before analyzing pages.
o365_auth_statusCheck whether the user is currently authenticated to Office 365 / SharePoint. Fast, no side effects — safe to call at any time.
o365_login_startStart the Office 365 device code sign-in flow. Returns a URL and code that the user must visit to authenticate. After the user signs in, call o365_login_complete to finish.
o365_login_completeWait for the user to complete the device code sign-in started by o365_login_start. Blocks until the user finishes signing in or the timeout is reached.
o365_logoutClear cached Office 365 tokens. The user will need to re-authenticate.
process_pdfLoad a PDF from a URL or local file path and inspect it. Returns metadata instantly — no image conversion. Use get_pages to retrieve actual page content as PDF.
get_pagesExtract pages from start_page to end_page (inclusive, 1-based).
save_pagesExtract pages and save as a PDF file to disk. Use this instead of get_pages when you need to read the pages via filesystem tools (e.g. copy_file_user_to_claude).
save_pages_as_imagesRender pages as PNG images and save to disk. Use this when Claude needs to visually read the drawings. After saving, use Filesystem copy_file_user_to_claude to pull the images into Claude's environment for viewing.
search_pdfSearch for text within a processed PDF. Case-insensitive. Returns matching pages with context snippets and bounding boxes.
cleanup_sessionDelete temporary files for a completed analysis session.
Tool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
11/11 tools missing one or more hints — get_analysis_prompt (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); o365_auth_status (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); o365_login_start (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +8 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Destructive tools are labelled
2 tools perform destructive updates without destructiveHint — process_pdf deletes at line 234 (shutil.rmtree(temp_dir, ignore_errors=True)); cleanup_session deletes at line 441 (shutil.rmtree(temp_dir, ignore_errors=True))
Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.
Descriptions match behaviour
1 tool describes read intent but its handler mutates — process_pdf (line 234: shutil.rmtree(temp_dir, ignore_errors=True))
Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.
Tool inputs are validated
7/11 tool handlers declare input schemas (64%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool handlers catch errors
Only 2/11 tool handlers wrap calls in try/catch (18%)
Wrap each tool handler body in try/catch and return a structured error response.
License file
No license file
Add a LICENSE file (MIT, Apache-2.0, etc.).
Tests exist
No test files found
Add tests that exercise each declared tool.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/viditjain123/arch-design-mcp)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check