northwood-carbon MCP server
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., "@northwood-carbon MCP server show me the three portcos with the largest gap to their 2030 targets"
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.
northwood-carbon MCP server
An MCP (Model Context Protocol) server that exposes Northwood Capital Partners' portfolio carbon data as tools any MCP-compatible agent (Claude Desktop, Claude Code, etc.) can call.
Turns carbon questions like "Which three portcos are furthest behind their 2030 targets, and what's the cheapest initiative for each?" into tool calls, not data wrangling.
Tools
Tool | Purpose |
| All 10 portcos with sector, status, revenue, facilities, data grade |
| Scope 1 / Scope 2 emissions for a portco, filterable by year + scope |
| Gap analysis vs SBTi-aligned 42% by 2030 pathway |
| Decarbonization levers with reduction, capex, status |
| What-if: apply initiatives, return projected emissions + capex |
Related MCP server: Sablier MCP Server
Install
# Clone
git clone <repo-url> northwood-carbon-mcp
cd northwood-carbon-mcp
# With uv (recommended)
uv sync
# Or with pip
pip install -e .Run
uv run server.py
# or
python server.pyThe server speaks MCP over stdio, so you don't run it directly in most cases — you register it with a client that spawns it.
Connect to Claude Desktop / Claude Code
Add to your MCP config (~/.claude/mcp.json or Claude Desktop settings):
{
"mcpServers": {
"northwood-carbon": {
"command": "uv",
"args": ["--directory", "/path/to/northwood-carbon-mcp", "run", "server.py"]
}
}
}Restart the client. The five tools appear automatically.
Example session
You: What are Meridian's 2024 Scope 1 emissions?
Claude → get_portco_emissions(portco="meridian", year=2024, scope=1)
← {"emissions": {"2024": {"scope1": 750.0}}, "units": "tCO2e", ...}
Claude: Meridian Business Solutions emitted 750 tCO2e in Scope 1 during 2024,
primarily natural gas for space heating across 16 offices.You: Which portcos are off-track for 2030 and what's the cheapest initiative for each?
Claude → list_portcos()
→ gap_to_target(portco=<each>) × 10
→ list_initiatives(portco=<off-track one>, status="planned") × 3
← synthesizes ranked answer with capex + reduction per leverData
Static snapshot in data.json, sourced from the Northwood engagement's Week 3 carbon
inventory and Week 4 decarbonization work. Drop in a live DB connection by replacing
the DATA = json.loads(...) line with a query layer — the tool surface stays identical.
Structure
.
├── server.py — FastMCP server, 5 tools, ~200 LOC
├── data.json — Static data (PORTCOS, TRAJECTORY, INITIATIVES, RISK_SUMMARY, ESG_SCORES, FACILITIES)
├── pyproject.toml
└── README.mdAvailable Tools
5 toolsgap_to_targetA
Compute gap between current trajectory and SBTi-aligned reduction target.
Uses latest forecasted annual total and compares against the pro-rated linear pathway from base year to target year.
Args: portco: Portco slug or name. target_year: Year to evaluate against (default 2030).
Returns: Dict with: current_tco2e, target_tco2e, gap_tco2e, gap_pct, on_track (bool), verdict (short string).
Inputs: portco (required), target_year. Returns: object
get_portco_emissionsA
Get Scope 1 and Scope 2 emissions for a specific portfolio company.
Args: portco: Portco slug (e.g. 'meridian') or name substring (e.g. 'Meridian'). year: Optional. Restrict to a single year (e.g. 2024). If omitted, returns totals for every available year. scope: Optional. 1 or 2 to filter to a single scope. If omitted, returns both.
Returns: Dict with portco metadata and an 'emissions' map of {year: {scope1, scope2, total}} in tCO2e. Values are tonnes CO2-equivalent.
Inputs: portco (required), year, scope. Returns: object
list_initiativesA
List decarbonization initiatives with estimated reduction, capex, and payback.
Args: portco: Optional. Filter to a single portco. If omitted, returns all portfolio initiatives. status: Optional. One of 'planned', 'in_progress', 'complete'.
Returns: List of initiative dicts: {portco, id, name, category, status, est_reduction_tco2e, capex_k, start_date}.
Useful for cost-curve analysis, payback screening, and status roll-ups.
Inputs: portco, status. Returns: result
list_portcosA
List all 10 Northwood portfolio companies with sector, status, and headline metrics.
Returns a list of dicts containing: slug, name, sector, fund, status, revenue ($M), ebitda ($M), facilities count, data_grade, base_year, target_year, target_reduction_pct.
Use this as the starting point for portfolio-level questions.
Inputs: no named parameters. Returns: result
simulate_reductionA
What-if analysis: apply a subset of initiatives and return projected post-lever emissions.
Args: portco: Portco slug or name. initiative_ids: List of initiative IDs (from list_initiatives) to 'turn on'.
Returns: Dict with baseline (current trajectory endpoint), applied initiatives, total reduction, total capex, and new endpoint vs target.
Inputs: portco (required), initiative_ids (required). Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool has a clearly distinct purpose: listing portfolio companies, retrieving emissions data, listing initiatives, simulating reductions, and computing gap to target. No overlap or ambiguity.
Four tools use a consistent verb_noun pattern (list_portcos, get_portco_emissions, list_initiatives, simulate_reduction). However, 'gap_to_target' starts with a noun rather than a verb, creating a minor inconsistency.
5 tools is an appropriate size for a focused carbon analysis server. Each tool serves a distinct function without unnecessary duplication or gaps.
The tool set covers the core analysis workflow: list companies, retrieve emissions, view initiatives, simulate reductions, and check targets. Missing write operations (e.g., create/update initiatives) but reasonable for a read/analysis-oriented server.
Maintenance
Related MCP Connectors
MCP server for VC pitch-deck scoring, thesis-fit matching, and deal-flow management.
MCP server for building and testing AI agents with multi-model experimentation and insights.
MCP server connecting AI agents to non-custodial staking data across 130+ networks.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Related MCP Servers
AlicenseBqualityDmaintenanceMCP server enabling AI assistants to automatically perform carbon footprint modeling, product queries, and emission analysis via the Carbonstop Cloud API.810 npmMIT
Sablier MCP Serverofficial
AlicenseAqualityDmaintenanceAn MCP server that lets AI assistants analyze portfolios, stress-test scenarios, generate synthetic market paths, and scan SEC filings — in under 2 minutes.833MIT- FlicenseNot gradedqualityDmaintenanceThis MCP server provides authentication via wallet sign-in (SIWE) and authorization with scoped access to read and trade portfolios, enabling secure portfolio management through natural language.-
- AlicenseNot gradedqualityCmaintenanceMCP server for the Carbon Interface API (v1), enabling AI agents to estimate carbon emissions through natural language queries via Pipeworx gateway.60 npmMIT