Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the EMIS Bappenas MBG, 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%2Fdevflocks.id%2Fdevflocks" | 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%2Fdevflocks.id%2Fdevflocks" | 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 EMIS Bappenas MBG API.
List education-unit records for Islamic boarding schools (pondok pesantren)
List education-unit records for madrasah
List education-unit records for other religious-affiliated schools
Read district-level figures for Islamic boarding schools
Read district-level figures for madrasah
GET STARTED
Read district-level figures for religious schools
Patterns agents use EMIS Bappenas MBG API for, with concrete tasks.
★ Agent-Driven Meal-Program Planning Data
An AI agent gathers the religious-education figures Bappenas uses to plan the free-meal program by reading the unit-level records for pesantren, madrasah, and religious schools and the matching district aggregates. The agent assembles a per-region view so a planning assistant can estimate how many education units a meal rollout would cover.
Read the unit-level and district-level records for madrasah and return the number of units per district
District-Level Aggregation
Build a district view of religious education by pulling the kabupaten-level figures for each institution type. A dashboard can then show how pesantren, madrasah, and religious schools are distributed across regions without summing unit records by hand.
Read the district-level figures for all three institution types and return a per-district total
Institution-Type Comparison
Compare Islamic boarding schools, madrasah, and other religious schools side by side by reading each type's education-unit records. This supports analysis of how the three categories differ in count and spread for program targeting.
Read the unit records for pesantren, madrasah, and religious schools and summarise the count of each type
6 endpoints — the emis bappenas mbg api serves indonesian religious-education data used to plan the makan bergizi gratis (free nutritious meals) program.
METHOD
PATH
DESCRIPTION
pendidikan_bappenas/satpend_ponpes
Education units for Islamic boarding schools
pendidikan_bappenas/satpend_madrasah
Education units for madrasah
pendidikan_bappenas/satpend_keagamaan
Education units for religious schools
pendidikan_bappenas/kabupaten_ponpes
District figures for Islamic boarding schools
pendidikan_bappenas/kabupaten_madrasah
District figures for madrasah
pendidikan_bappenas/kabupaten_keagamaan
District figures for religious schools
pendidikan_bappenas/satpend_ponpes
Education units for Islamic boarding schools
pendidikan_bappenas/satpend_madrasah
Education units for madrasah
pendidikan_bappenas/satpend_keagamaan
Education units for religious schools
pendidikan_bappenas/kabupaten_ponpes
District figures for Islamic boarding schools
pendidikan_bappenas/kabupaten_madrasah
District figures for madrasah
pendidikan_bappenas/kabupaten_keagamaan
District figures for religious schools
What agents get from Jentic-routed access to this vendor.
Setup
The API needs no sign-up and no key, but by hand you still wire its base host, learn the Indonesian field names, and handle the six separate datasets yourself. Through Jentic you install once, import it from the API Directory, and your agent reads the datasets by intent.
Permission scoping
Every operation is a read-only GET for one institution type at one level, so you choose exactly which datasets your agent may read, such as madrasah figures while leaving out the rest. Each call is logged for review.
Credential isolation
This API requires no credential, so your agent holds nothing sensitive to read it. For any credentialed API you add beside it, your own Jentic One instance keeps that secret encrypted and injects it at execution time, never in the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'madrasah education units' or 'district religious-school figures', and Jentic returns the matching EMIS Bappenas 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 EMIS Bappenas MBG API through Jentic.
What authentication does the EMIS Bappenas MBG API use?
The API is open: its OpenAPI spec declares no security scheme, so the endpoints need no API key or token and you can call them straight away. When you connect it through Jentic alongside APIs that do need keys, those other secrets stay encrypted on your own Jentic One instance.
What data does the EMIS Bappenas MBG API return?
It returns religious-education figures for the Makan Bergizi Gratis program: unit-level records for Islamic boarding schools, madrasah, and other religious schools, plus the same figures aggregated by district. Every endpoint is a read-only GET over this reference data.
What are the rate limits for the EMIS Bappenas MBG API?
The OpenAPI spec does not specify rate limits. Confirm any usage limits with the data provider before running repeated bulk reads, since the endpoints return reference datasets rather than per-record lookups.
How do I read Bappenas education data through Jentic?
Add the EMIS Bappenas MBG API from the Jentic API Directory, then have your agent search by intent such as 'madrasah education units' and call the matching operation. Because the data is open, there is no credential step. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Can I limit which datasets my agent is allowed to read?
Yes. Every operation is a read-only GET for one institution type at one level, so you grant your agent only the datasets it needs, such as madrasah figures, and leave out the rest. Each call the agent makes is logged, so you can see exactly which datasets it read.
Is there an EMIS Bappenas MBG MCP server?
You don't need an MCP server to give your agent this data. Jentic connects the EMIS Bappenas MBG API directly from the API Directory: import it and your agent can read the education datasets right away, without another server loading tool definitions into its context.
Know of an official OpenAPI document? Contribute it →
For Agents
Read Indonesian religious-education data for the Bappenas MBG meal program: unit-level records for Islamic boarding schools, madrasah, and religious schools, plus the same figures aggregated by district.
Use for: List all pondok pesantren education units, Get the madrasah data for the MBG program, I want district-level counts of religious schools, Retrieve education-unit records for Islamic boarding schools
Not supported: Does not cover general schools, enrolment, or individual student records, and does not write data. Use for reading Bappenas Islamic-education unit and district figures for the MBG program only.
The EMIS Bappenas MBG API serves Indonesian religious-education data used to plan the Makan Bergizi Gratis (free nutritious meals) program. You read education-unit records for Islamic boarding schools (pondok pesantren), madrasah, and other religious-affiliated schools, and you read the same figures aggregated at the district (kabupaten) level. It is a read-only reference layer over the education data Bappenas needs to size and target the meal program across regions.
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>