For Agents
Read a registry of published learning guides: list guides, fetch one by slug, search the registry, and read the taxonomy, capability spine, and cross-book disagreements. All operations are read-only.
Use for: List all published guides in the registry, Get a guide by its slug, Search the guide registry for a topic, Retrieve the guide taxonomy
Not supported: Does not author guide content, track learner progress, or issue credentials. Use for reading the published-guide registry, its taxonomy, and capability mappings only.
The Bicycle Guide Registry API serves read-only metadata about published learning guides, their taxonomy, and the capability spine that links books, guides, KSAO elements, and jobs. It lists the registry, returns a single guide's row by slug, and searches guides or returns the nearest owned guide when none matches. Supporting endpoints expose the program's taxonomy, organizational conditions, and cross-book disagreements for cooperating repositories and agents.
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the bicycle.guide guide registry 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%2Fdataengineerprofessional.com%2Fdataengineerprofessional" | 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%2Fdataengineerprofessional.com%2Fdataengineerprofessional" | 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 bicycle.guide guide registry API.
List the published-guide registry with each guide's metadata
Retrieve a single guide's registry row by its slug
Search guides, or get the nearest owned guide when none matches
Read the guide program's taxonomy as structured data
Query the capability spine linking books, guides, KSAO elements, and jobs
Read organizational conditions with their identity, label, and provenance
List cross-book disagreements for a guide with names and provenance
Patterns agents use bicycle.guide guide registry API for, with concrete tasks.
★ Agent Lookups Against the Guide Registry
An AI agent connected through Jentic can answer questions about published guides without a developer wiring the calls: it searches the registry for a topic, fetches the top guide's row by slug, and reads that guide's cross-book disagreements to see where sources differ. Because the registry is read-only, the agent can query it freely to ground its answers in the published metadata.
Search the guide registry for a topic, fetch the top guide's row by slug, and read its cross-book disagreements
Taxonomy and Capability Mapping
Teams building on the guide program use the taxonomy and capability spine to connect guides to jobs and competencies. The taxonomy endpoint returns the program's vocabulary as data, and the capability spine links books, guides, KSAO elements, and jobs. An agent can read both to map a guide onto the jobs it supports.
Read the taxonomy and query the capability spine to list the jobs a given guide supports
Registry Synchronisation for Cooperating Repos
Cooperating repositories keep a local view of the guide program in sync by reading its control-plane metadata. An agent lists the full registry and the taxonomy and copies them into a local store so other services share one source of truth. The read-only shape makes the sync safe to run on a schedule.
List the full guide registry and the taxonomy to synchronise a cooperating repository's local copy
8 endpoints — the bicycle guide registry api serves read-only metadata about published learning guides, their taxonomy, and the capability spine that links books, guides, ksao elements, and jobs.
METHOD
PATH
DESCRIPTION
/api/v1/guides
List the guide registry
/api/v1/guides/{slug}
Get one guide's registry row
/api/v1/guides/search
Search guides or return the nearest owned guide
/api/v1/taxonomy
Read the program's taxonomy
/api/v1/capabilities
Query the capability spine
/api/v1/conditions
Read organizational conditions
/api/v1/guides
List the guide registry
/api/v1/guides/{slug}
Get one guide's registry row
/api/v1/guides/search
Search guides or return the nearest owned guide
/api/v1/taxonomy
Read the program's taxonomy
/api/v1/capabilities
Query the capability spine
/api/v1/conditions
Read organizational conditions
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>What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Bicycle Guide Registry API by hand means handling its shared-secret header on every route and the registry, taxonomy, and capability-spine shapes it returns. Through Jentic you install once, import it from the API Directory, store the secret once, and your agent calls it.
Permission scoping
The Bicycle Guide Registry API is read-only and puts the guide slug in the URL path, so a rule can pin your agent to one guide's reads or to the registry and taxonomy endpoints it needs. No operation can write, so a scoped agent can only read.
Credential isolation
Your Bicycle Guide secret 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 'find a guide' or 'read the taxonomy', and Jentic returns the matching Bicycle Guide operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using bicycle.guide guide registry API through Jentic.
What authentication does the Bicycle Guide Registry API use?
The API authenticates with a shared-secret API key per its OpenAPI spec: every route requires the secret in the x-bicycle-guide-secret request header. Through Jentic the secret is stored once, encrypted, by your own Jentic One instance and injected at call time.
Can I search the guide registry with the Bicycle Guide Registry API?
Yes. You can list the full registry, fetch a guide by slug, and run a search that returns matching guides or the nearest owned guide when none matches. The taxonomy and capability spine let you map a guide to its vocabulary and to jobs.
What are the rate limits for the Bicycle Guide Registry API?
The OpenAPI spec does not define rate limits for the Bicycle Guide Registry API. Check the Bicycle Guide documentation at https://bicycle.guide/docs for current limits.
Is there a Bicycle Guide Registry MCP server?
Yes, the same registry data is also served over its own MCP endpoint. You can also connect it directly through Jentic: your agent gets the full 8-endpoint surface without loading another server's tool definitions into its context, your secret is injected at call time by your self-hosted instance instead of living in a config file, and your rules decide which operations the agent may call.
Can I limit what my agent is allowed to do with the Bicycle Guide Registry API?
Yes. Every operation is a read, so a rule can allow just the registry and taxonomy reads your agent needs and nothing can modify data. Because the operations are read-only, the worst an over-broad rule allows is reading more of the registry. Every call the agent makes is logged.
How do I read the guide registry with the Bicycle Guide Registry API through Jentic?
Search Jentic for 'search the guide registry', and it returns the matching operations with their input schemas. Your agent searches guides, fetches a guide by slug, and reads the taxonomy in one run. To run it on your own infrastructure, install Jentic One from its GitHub repo.
GET STARTED