mcp · Global

construction-claude-cowork-project-indexer

Co-work skill that builds a full AI context system for construction projects. 20-40x fewer tokens. Consistent answers across every chat.

Visit source ↗GitHub repository ↗

Claim this listing

Represent construction-claude-cowork-project-indexer? Send a claim for review so we can discuss listing updates. Claims do not automatically grant ownership or verification.

Explore paid sponsorship →

What's in it

Data offered docs-verified: drawing sheet text layer (CAD-exported PDFs) · scanned-sheet flag for image-only sheets · per-sheet PDF split from merged drawing PDF · per-sheet PNG render for vision · drawings.md sheet register and symbol library · project.md project snapshot · claude.md instruction file · memory.md running project log
Resolution docs-verified: PNG rendered at 2x resolution per sheet; no spatial or ground resolution stated
Update frequency docs-verified: Index built once per project; memory.md updated at end of chats when prompted
Formats llm-inferred: PDF · TXT · PNG · Markdown
Access docs-verified: Requires the Claude desktop app with Co-work; business-context connectors (Notion, Google Drive or GitHub) optional but recommended; licence 'Other' per catalogue metadata, not stated in docs

Useful for

Use cases llm-inferred: Build a drawing register so RFI drafts cite the correct sheet and read only that sheet's PNG or text · Create a project.md snapshot of contract terms, parties and milestones for a new civils or infrastructure project · Extract programme and BOQ data into structured tables for estimate or variation-claim prep
Audience llm-inferred: contracts managers · quantity surveyors · civils engineers · project controls teams · BIM coordinators

Limitations

Constraints llm-inferred: Catalogue kind is 'mcp', but the docs describe a Co-work skill (SKILL.md) and name no MCP tools · Built for construction firms; no UK, water or environmental data scope is stated · First run can take 15–60 minutes depending on project size · Image-only (scanned) sheets get a flag rather than extracted text · Business-context features need a Notion, Google Drive or GitHub connector · The 20–40x token saving is the author's claim, not independently verified

Licence: Other
Authentication: Unknown — review source docs
GitHub stars: 9
Last commit: 02/08/2026
Last successful page check: 14/10/2026
Page health: healthy
Package: Not recorded
Verification: Not independently verified

Auto-extracted, unverified fields: tools, auth. Check upstream documentation.

Provenance & evidence

Daily discovery 2026-10-15: GitHub search; verified via GitHub API. Tools/install/auth auto-extracted from README.

Metadata observed 14/10/2026 · daily-2026-10-15 (github-search)