Koskamo

CivilQuants MCP

An official MCP server for CivilQuants, a Bill of Quantities software for civil engineering. It allows AI assistants to generate measured bills based on UK standards (CESMM4, NRM2, SMM7, MMHW) and produce supplier-neutral material schedules for procurement by entering assembly geometry.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

CivilQuants MCP logo, by Ember Forge Pte LtdVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-06Operated by Ember Forge Pte Ltd
MCP endpoint (Streamable HTTP)
https://api.civilquants.com/mcp
Vendor documentation

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Passed Official MCP Registry namespace is tied to civilquants.com ·
  • Passed Endpoint is on the registry namespace domain ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Generate Bills of Quantities for civil assemblies
  • Produce supplier-neutral material schedules
  • Export bills to Excel or PDF formats
  • Apply senior-QS skill methodologies

Source and maintenance

Vendor evidenceRegistry 0.0.1
mcp-registry: com.civilquants/civilquants@0.0.1

Protocol and capabilities

Server
civilquants 3.4.7
MCP protocol negotiated in check
2025-11-25
Tools
0 captured; incomplete (byte-cap)
Resources
8 advertised
Resource templates
0 advertised
Prompts
11 advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": true
  },
  "logging": {},
  "prompts": {
    "listChanged": true
  },
  "resources": {
    "subscribe": false,
    "listChanged": true
  },
  "extensions": {
    "io.modelcontextprotocol/ui": {}
  },
  "experimental": {}
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

CivilQuants — QS-grade parametric estimating engine. Exposes 46 compute_<slug> tools (one per assembly), a render_skill_report tool for BoQ deliverables (Excel + Word), four project tools (save_project, get_project, list_projects, recompute_project) for paid-tier subscribers, and ten senior-QS skill methodologies (tender review + risk, QS measurement/contract advice, geotechnical + geo-environmental interpretation, earthworks, preliminaries, pavement design, subcontract analysis) reachable via the list_skills + get_skill tools (paid tier). The document-heavy skills require a code-execution client (Claude Code / Codex / VS Code) and the chunking pack from get_document_pipeline to run a real tender pack — on a chat connector you can read the methodology but cannot chunk/parse documents; the Word adjudication pack renders customer-side via word-report-base (get_document_pipeline component='render'), not server-side. Anonymous callers may use the six free-tier compute tools (attenuation_tank, cantilever_wall, end_area_earthworks, gully, headwall, manhole) and the Excel render skill — all other tools return a TIER_INSUFFICIENT envelope until OAuth-based subscription resolution lights up. The free tier renders the MMHW standard only; CESMM4, NRM2 and SMM7 require a paid tier. Saved projects: save_project creates a new project each call; to revise a parameter, fetch the stored assemblies with get_project, amend them, call save_project again (suffix the name, e.g. 'R02'), then recompute — recompute_project takes no parameter overrides. In a later conversation, re-find saved work with list_projects or get_project by exact name. Pass deliverables=["xlsx","dxf","pdf"] (any subset) on a compute call for one-shot download URLs: Excel BoQ (both tiers) plus dimensioned DXF + PDF drawing sheets (paid tier). For linear assemblies (pipe runs, kerbs, drains, barriers, channels), always confirm the run length with the user before computing — quantities scale directly with it and an unstated run length is the most common source of error. Read civilquants://intro for positioning and the free/paid boundary, and civilquants://catalogue for the full assembly picker with tiers. A compute response is large; pass output_mode='summary' or 'boq' to get a trimmed payload in chat (default returns the full result). For a procurement take-off (what to order — the aggregate quantity of each material, no priced bill), pass output_mode='material_schedule'. Trimmed modes null already-computed fields (the dimensioned drawing, the audit trail, sometimes the bill rows) to save tokens — that is paring, NOT a missing capability; _meta.output_mode lists what was omitted and the mode that returns it. Example: "Measure a 1200 mm manhole 3 m deep to MMHW." Not sure which tool to call? Describe the job in words and call resolve_assembly_from_description — it routes you to the right assembly and lists the fields you'll need, then you call compute_<slug>.

Tools

0 captured; incomplete (byte-cap)

No tool definitions available.

Prompts

11 advertised

tender_document_review — Tender Document Review

Advertised by the server during the last successful anonymous check.

Paid tier only. Master 15-section tender review orchestrator (dispatches sub-skills). Anonymous callers get a TIER_INSUFFICIENT upsell body; paid callers get the full methodology. Sign up at https://civilquants.com/pricing.

No arguments advertised.

tender_risk_assessment — Tender Risk Assessment

Advertised by the server during the last successful anonymous check.

Paid tier only. Structured risk register + bid/no-bid score per ISO 31000. Anonymous callers get a TIER_INSUFFICIENT upsell body; paid callers get the full methodology. Sign up at https://civilquants.com/pricing.

No arguments advertised.

qs_measurement_advice — QS Measurement Advice

Advertised by the server during the last successful anonymous check.

Paid tier only. Bill descriptions / measurement-rule advice (SMM7 / NRM2 / CESMM4 / MMHW). Anonymous callers get a TIER_INSUFFICIENT upsell body; paid callers get the full methodology. Sign up at https://civilquants.com/pricing.

No arguments advertised.

qs_contract_review — QS Contract Review

Advertised by the server during the last successful anonymous check.

Paid tier only. Contract administration questions (JCT 2024 / NEC4 ECC) — payment, variations, claims. Anonymous callers get a TIER_INSUFFICIENT upsell body; paid callers get the full methodology. Sign up at https://civilquants.com/pricing.

No arguments advertised.

geotechnical_interpretation — Geotechnical Interpretation

Advertised by the server during the last successful anonymous check.

Paid tier only. Ground investigation reports → design parameters per BS 5930 / SHW 600 / TRL447. Anonymous callers get a TIER_INSUFFICIENT upsell body; paid callers get the full methodology. Sign up at https://civilquants.com/pricing.

No arguments advertised.

geo_environmental_assessment — Geo-environmental Assessment

Advertised by the server during the last successful anonymous check.

Paid tier only. Site investigation contamination → assessment per LCRM / WM3 / BS 8485 / CL:AIRE. Anonymous callers get a TIER_INSUFFICIENT upsell body; paid callers get the full methodology. Sign up at https://civilquants.com/pricing.

No arguments advertised.

earthworks_quantities — Earthworks Quantities

Advertised by the server during the last successful anonymous check.

Paid tier only. Cut / fill, mass-haul, plant outputs, disposal economics, SHW Series 600. Anonymous callers get a TIER_INSUFFICIENT upsell body; paid callers get the full methodology. Sign up at https://civilquants.com/pricing.

No arguments advertised.

preliminaries_setup — Preliminaries Setup

Advertised by the server during the last successful anonymous check.

Paid tier only. Site-establishment costing per NRM2 / CESMM4 / MMHW + CDM 2015. Anonymous callers get a TIER_INSUFFICIENT upsell body; paid callers get the full methodology. Sign up at https://civilquants.com/pricing.

No arguments advertised.

pavement_design_review — Pavement Design Review

Advertised by the server during the last successful anonymous check.

Paid tier only. UK pavement design drawings → layered quantities + spec compliance (DMRB / SHW). Anonymous callers get a TIER_INSUFFICIENT upsell body; paid callers get the full methodology. Sign up at https://civilquants.com/pricing.

No arguments advertised.

subcontract_quotation_analysis — Subcontract Quotation Analysis

Advertised by the server during the last successful anonymous check.

Paid tier only. Sub quote breakdown + gap analysis + normalised comparison + weighted scoring. Anonymous callers get a TIER_INSUFFICIENT upsell body; paid callers get the full methodology. Sign up at https://civilquants.com/pricing.

No arguments advertised.

getting-started — CivilQuants — Getting started

Advertised by the server during the last successful anonymous check.

Free + paid. Agent-coaching prompt for a first-time CivilQuants connection: how to turn discovery into a concrete first call with a real deliverable. Invoke after connecting to the MCP.

No arguments advertised.

Resources

8 advertised

CivilQuants — Introduction

Advertised by the server during the last successful anonymous check.

One-pager describing the MCP: free vs paid scope, the four-standard methodology moat, and where to start.

CivilQuants — Introduction URI
civilquants://intro

MIME type: text/markdown

CivilQuants — MCP schema (v1)

Advertised by the server during the last successful anonymous check.

Machine-readable contract: every registered tool's input/output JSON Schema plus the resource + prompt catalogue. Read this to assert the live MCP matches your client's static expectations.

CivilQuants — MCP schema (v1) URI
civilquants://schema/v1

MIME type: application/json

CivilQuants — Assembly catalogue

Advertised by the server during the last successful anonymous check.

Picker tree (L1 category → L2 subcategory → assembly) for the 46 v1 assemblies. Identical shape to the live web-UI picker; use this to map user-stated problems to the right compute_<slug> tool.

CivilQuants — Assembly catalogue URI
civilquants://catalogue

MIME type: application/json

CivilQuants — Document-pipeline discipline

Advertised by the server during the last successful anonymous check.

Chunking + render discipline for customer-side processing of tender packs, GI reports, and other source documents before passing chunks into the paid-tier skill prompts. ~400 lines.

CivilQuants — Document-pipeline discipline URI
civilquants://document-pipeline-discipline

MIME type: text/markdown

CivilQuants — Document-pipeline starter (Python)

Advertised by the server during the last successful anonymous check.

Reference Python invocation of the chunking pipeline. Pairs with civilquants://tools/document-pipeline-manifest.md and the document-pipeline-discipline doc. Customer-side; no LLM in the loop until the SkillDispatcher is wired.

CivilQuants — Document-pipeline starter (Python) URI
civilquants://tools/document-pipeline-starter.py

MIME type: text/x-python

CivilQuants — Document-pipeline manifest

Advertised by the server during the last successful anonymous check.

Package manifest for the chunking pipeline: PipelineConfig + PipelineResult + SkillDispatcher Protocol + module layout. Read this to rebuild the deterministic pipeline yourself.

CivilQuants — Document-pipeline manifest URI
civilquants://tools/document-pipeline-manifest.md

MIME type: text/markdown

CivilQuants — Word report base template

Advertised by the server during the last successful anonymous check.

python-docx base template every skill report extends. Customer-side LLM uses this + the skill output to render a CivilQuants-co-branded Word report on the customer's machine.

CivilQuants — Word report base template URI
civilquants://tools/word-report-base.md

MIME type: text/markdown

CivilQuants — Chunking pack (self-unpacking bundle)

Advertised by the server during the last successful anonymous check.

The full reference civilquants_chunking Python package (6 modules + requirements.txt) in one self-unpacking bundle. Write each fenced block to its labelled path, pip install, then run document-pipeline-starter.py. Makes the document-heavy skill prompts usable on a real tender pack.

CivilQuants — Chunking pack (self-unpacking bundle) URI
civilquants://tools/chunking-pack

MIME type: text/markdown

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (3 of 3 answered).

  1. 2026-11-06: 1 of 1 checks answered
  2. 2026-11-07: 2 of 2 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
2556 ms
95th percentile latency
2556 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 2556 ms · metadata changed · 0 tool(s) (partial: byte-cap), 8 resource(s), 0 resource template(s), 11 prompt(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http civilquants-mcp https://api.civilquants.com/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add civilquants-mcp --url https://api.civilquants.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable civilquants-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "civilquants-mcp": {
      "url": "https://api.civilquants.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "civilquants-mcp": {
      "type": "streamableHttp",
      "url": "https://api.civilquants.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start civilquants-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "civilquants-mcp": {
      "type": "http",
      "url": "https://api.civilquants.com/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http civilquants-mcp https://api.civilquants.com/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://api.civilquants.com/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "civilquants-mcp": {
      "serverUrl": "https://api.civilquants.com/mcp"
    }
  }
}

Let your agent find its tools

Find servers like CivilQuants MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 7,107

Do you run CivilQuants MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing