Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the GreenCalculus API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fgreencalculus.com%2Fgreencalculus" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fgreencalculus.com%2Fgreencalculus" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with GreenCalculus API.
Resolve a greenhouse-gas emission factor by canonical key with full provenance
Convert activity data into emissions with unit conversion and working shown
Calculate whole-life embodied carbon under EN 15978
Compute PCAF Part A financed emissions with an audit trail
Report Scope 2 electricity emissions with location and market methods
GET STARTED
Watch factor keys and read what changed between data releases
Patterns agents use GreenCalculus API for, with concrete tasks.
★ Agent-run carbon accounting
An AI agent can compute an organization's emissions through GreenCalculus by resolving the right emission factor, converting activity data into emissions with the working shown, and citing the exact source reference and data version for each value. Because every result carries provenance, the agent's output is auditable. Connected through Jentic, the agent calls only the calculation and lookup operations it needs.
Resolve the emission factor for an activity, calculate its emissions with unit conversion, and return the source reference and data version
Financed and embodied emissions
Sustainability teams need methodology-specific calculations they can defend in an audit. GreenCalculus computes PCAF Part A financed emissions with an attribution audit trail and whole-life embodied carbon under EN 15978, each boundary-aware. An agent can run these for a portfolio or a building and keep the audit trail attached.
Compute PCAF Part A financed emissions for a holding and return the attribution and audit trail
Factor change tracking
Emission factors are revised between data releases, and a reported number can drift out of date. GreenCalculus exposes a change feed and a per-account watch list, so an agent can watch the factor keys a report depends on and read exactly what each release changed. The coverage endpoint shows which countries hold data.
Watch a factor key and read what changed for it between two data release dates
29 endpoints — the greencalculus api resolves sourced greenhouse-gas emission factors and turns activity data into audit-traced carbon calculations, each value returned with its exact source reference and data version.
METHOD
PATH
DESCRIPTION
/v1/factors/{key}
Resolve one factor by canonical key
/v1/factors
Browse or search the factor corpus
/v1/calculate/ghg-activity
Convert an activity into emissions
/v1/calculate/embodied
Calculate whole-life embodied carbon
/v1/calculate/pcaf
Compute PCAF Part A financed emissions
/v1/calculate/batch
Run up to 100 mixed-methodology calculations
/v1/changes
Read the change feed across data releases
/v1/factors/{key}
Resolve one factor by canonical key
/v1/factors
Browse or search the factor corpus
/v1/calculate/ghg-activity
Convert an activity into emissions
/v1/calculate/embodied
Calculate whole-life embodied carbon
/v1/calculate/pcaf
Compute PCAF Part A financed emissions
/v1/calculate/batch
Run up to 100 mixed-methodology calculations
/v1/changes
Read the change feed across data releases
What agents get from Jentic-routed access to this vendor.
Setup
Wiring GreenCalculus by hand means handling its Bearer key, picking the right calculation endpoint per methodology, and threading the data version through each result yourself. Through Jentic you install once, import GreenCalculus from the API Directory, store the key once, and your agent calls it.
Permission scoping
GreenCalculus carries activity inputs and factor keys in the path and body, so a rule bounds which operations your agent may call rather than which factor. You choose the operations it may call, so the watch-list operations are not included unless you add them.
Credential isolation
Your GreenCalculus key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'calculate activity emissions' or 'resolve an emission factor', and Jentic returns the matching GreenCalculus operation with its input schema so the agent calls the right endpoint without reading the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using GreenCalculus API through Jentic.
What authentication does the GreenCalculus API use?
GreenCalculus authenticates with your API key as a Bearer token in the Authorization header, per its OpenAPI spec. Several public endpoints, such as health, factor browse, coverage, and the change feed, need no key. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at execution time.
Can I calculate emissions with provenance using the GreenCalculus API?
Yes. The activity calculation returns emissions with unit conversion and the working shown, and every value comes back with its exact source reference and data version. Methodology-specific endpoints cover embodied carbon under EN 15978, PCAF Part A financed emissions, and Scope 2 electricity.
What are the rate limits for the GreenCalculus API?
The OpenAPI spec does not publish fixed per-second rate limits, and the batch endpoint accepts up to 100 mixed-methodology calculations in one call. Check https://greencalculus.com/developers/ for current limits.
How do I calculate activity emissions with the GreenCalculus API through Jentic?
Search Jentic for 'calculate activity emissions' and it returns the GreenCalculus activity-calculation operation with its input schema, so your agent fills the body and calls it. Install Jentic One with `curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh`, import GreenCalculus from the API Directory, and store your key once. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Can I limit what my agent is allowed to do with GreenCalculus?
Yes. Write a rule that allows only the calculation and factor-lookup operations, so the agent can compute emissions and resolve factors but cannot change your watch list, and every call it makes is logged.
Is there a GreenCalculus MCP server?
You don't need an MCP server to connect your agent to GreenCalculus. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent discovers and calls the operations it needs on demand.
For Agents
Lets an AI agent resolve sourced emission factors and compute audit-traced greenhouse-gas emissions across several methodologies, each with provenance.
Use for: Resolve an emission factor by its canonical key, Get the emissions for an activity with the working shown, Calculate the embodied carbon of a material, Compute financed emissions for a portfolio under PCAF
Not supported: Does not handle carbon offset purchasing, utility billing, or ESG report filing. Use for sourced emission factors and greenhouse-gas calculations only.
The GreenCalculus API resolves sourced greenhouse-gas emission factors and turns activity data into audit-traced carbon calculations, each value returned with its exact source reference and data version. Calculation endpoints cover activity emissions, EN 15978 embodied carbon, PCAF Part A financed emissions, Scope 2 electricity, freight, spend-based, and business travel, with a batch endpoint for mixed methodologies. It also exposes a factor corpus, coverage, a change feed, and a per-account watch list for tracking factor updates.
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>