io.github.jdhart81Published by GitHub account jdhart81v0.1.0Updated Nov 2, 2026
Carbon-accounted agent compute: free footprints; certificates backed by real offset retirement.
The publisher's own server: 370.ai — AI Gateway: 100+ Chat Models, Image & Speech Generation
Estimates the energy and carbon footprint of an AI workload, ranks backends by carbon, and issues paid offset-retirement certificates.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.jdhart81%2Fgreen-router/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Add this to your client's mcpServers config.
{
"mcpServers": {
"green-router": {
"type": "http",
"url": "https://mcp.viridisconservation.com/green-router/mcp"
}
}
}Deterministic, auditable MCP agents: trust and settlement rails (identity, trust, escrow, metering, arbitration, notary, surety, provenance, covenant, offsets, compute-ledger) and priced-grade services (tax credits, GHG accounting, construction takeoff, measurement, compliance). Every core is pure Python with no LLM in the serving path, and every result is content-addressed so anyone can re-verify it.
Licensed Apache-2.0. Run any agent yourself, fork it, embed it.
https://mcp.viridisconservation.com runs all agents as one managed MCP service:
Free tier: 10 calls/day per service; the rails (identity, escrow, metering…) are free forever. Verification is always free.
Agents and LLM tools can start from llms.txt, a generated index of every agent, and AGENTS.md, the rules for using and changing the fleet.
Building agents for conservation or energy work? VergeCommon and EnergyAI MCP also expose MCP tools, and ViridisOS serves its decision functions to agents over MCP.
This project is one of a connected set of open tools from Viridis. Each stands on its own; together they run from field evidence to checked decisions.
Conservation commons
Verifiable science
Agent tools
Browse every project on the Viridis profile. If this one is useful to you, a star helps other people find it.
This repo contains agent cores, MCP adapters, tests, standards and self-host tooling. The hosted service layer (gateway, payment and settlement, seats, signing authority, operations, telemetry and customer data) is proprietary and is not in this repo. Please don't open PRs that add it.
"Viridis", "Viridis Conservation" and the Viridis marks are trademarks of Viridis LLC; see TRADEMARKS.md.
Source: README.md at commit 350712c
FREE: honest energy/carbon footprint for an agent workload — {backend_id? (frontier_cloud | efficient_cloud | local_small), total_tokens, output_tokens, calls?, success_score?, grid_gco2e_per_kwh?, pue?, custom_backend? {id, wh_per_1k_tokens}}. Returns joules, gCO2e, useful bits, the retirement mass a certificate would carry, every model assumption with its source, and the Landauer context (GR1/GR2).
workloadrequiredFREE: rank compute backends by carbon for this workload — the greenest eligible path and the gCO2e saved per call. Carbon only (GR6); pair with /neurogenesis/mcp route_task for quality-floor routing.
workloadrequiredallowed_backendsPAID ($0.50 after free tier): compute the workload footprint, then RETIRE the required verified offset mass through the fleet's own clearinghouse — Verra provenance rides into the certificate; no retirement, no certificate (GR3, fail-closed). Returns a machine-verifiable certificate anyone can check for free (GR4).
workloadrequiredrequest_idFREE forever (GR5): recompute a certificate's footprint from its stored workload, compare against the certified numbers, and surface the clearinghouse purchase_id for the independent x402-C verify_retirement check on /offsets/mcp.
certificate_idrequiredFREE: the certificate ledger — counts, total grams retired, total clearinghouse cost (honest books, GR8).
limitReturn capabilities and input contract.
Takes no parameters.
100% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
ai.routerOfficial publisher
Remote AI gateway MCP server that lets an assistant call 100+ chat models, generate images, and convert text to speech through one 370.ai API key.
Published by GitHub account jutsuhq
Local MCP server that generates images and videos through 40+ providers using your own API keys, with price comparison and a searchable local asset library.
Published by GitHub account JonasHeinickeBio
MCP bridge to a self-hosted pyBikeRouter API that plans OSM-based bike routes with weather, sights and GeoJSON/GPX exports.
Published by GitHub account Elnaril
Local MCP server that decodes and encodes Uniswap Universal Router calldata for V2, V3 and V4 swaps, read-only and never signing or sending.
Published by GitHub account camerxnduff
Read-only MCP server that searches a probed registry of live x402 pay-per-call endpoints and routes an agent to the best-scored one.
pip install -r requirements-dev.txtpython3 agent-escrow-agent/adapters/mcp_server.py # stdio MCPpython3 run_fleet_tests.py # every agent's invariant tests