For Agents
Look up Swiss companies from the commercial register: resolve a UID to full details, list officers and governing bodies, follow register events, and match or reconcile batches of up to 500 entities.
Use for: Find a Swiss company by its registered name, Look up a company's full details from its UID, List the officers of a Swiss legal entity, Match a list of company names to their UIDs
Not supported: Does not handle credit scoring, financial statements, or tax filings. Use for Swiss commercial register lookups and company identity resolution only.
The Firmenwatch API exposes the Swiss commercial register over REST, serving company records taken from the Zefix and LINDAS master data together with published notices from the Swiss Official Gazette of Commerce. It searches legal entities, resolves a single company by its UID, lists the officers and governing bodies on record, and streams register events as they are published. It also matches and reconciles batches of up to 500 companies, drives a resumable three-step portfolio sync, and prioritises review cases with optimistic version protection so concurrent edits do not clobber each other.
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Firmenwatch 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%2Ffirmenwatch.ch%2Ffirmenwatch" | 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%2Ffirmenwatch.ch%2Ffirmenwatch" | 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 Firmenwatch API.
Search the Swiss commercial register for a legal entity by name
Resolve a company's full register record from its UID
List the officers and governing bodies recorded for a company
Follow the register event stream to catch changes as they are published
Match up to 500 company names to their UIDs in a single request
Reconcile a portfolio of existing UIDs against the current register
Validate and normalize a Swiss UID
Patterns agents use Firmenwatch API for, with concrete tasks.
★ Agent-driven company lookup
An AI agent connected through Jentic resolves a Swiss company straight from the commercial register: given a UID it fetches the full record, lists the current officers and governing bodies, and reads the latest register events, returning a clean summary without the developer wiring the bearer auth or paging logic by hand.
Look up the Swiss company for a given UID, list its current officers, and summarize its most recent register events
Portfolio reconciliation
A monitoring tool keeps a book of Swiss entities current by submitting up to 500 UIDs to the reconcile endpoint and committing a resumable portfolio sync in one atomic step, so a dropped connection mid-upload never leaves the portfolio half-updated.
Submit a batch of up to 500 UIDs to the reconcile endpoint and commit a portfolio sync atomically
Register change monitoring
A compliance workflow creates a checkpoint on the event stream and then polls for new register events, matching unknown company names to UIDs as it goes, so changes of officers or legal status surface as soon as they are published in the Official Gazette of Commerce.
Create an event checkpoint, pull the register events published since it, and match any unknown company names to their UIDs
16 endpoints — the firmenwatch api exposes the swiss commercial register over rest, serving company records taken from the zefix and lindas master data together with published notices from the swiss official gazette of commerce.
METHOD
PATH
DESCRIPTION
/companies
Search the Swiss commercial register
/companies/{uid}
Resolve a company by its UID
/companies/{uid}/officers
List a company's officers and governing bodies
/companies/{uid}/events
List register events for a company
/companies/match
Match up to 500 names to UIDs
/companies/reconcile
Reconcile up to 500 existing UIDs
/events
Stream register events
/uid/validate
Validate and normalize a UID
/companies
Search the Swiss commercial register
/companies/{uid}
Resolve a company by its UID
/companies/{uid}/officers
List a company's officers and governing bodies
/companies/{uid}/events
List register events for a company
/companies/match
Match up to 500 names to UIDs
/companies/reconcile
Reconcile up to 500 existing UIDs
/events
Stream register events
/uid/validate
Validate and normalize a UID
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 Firmenwatch by hand means handling its bearer-token auth, the resumable three-step portfolio sync, and optimistic version checks on review cases yourself. Through Jentic you install once, import Firmenwatch from the API Directory, store the token once, and your agent calls it.
Permission scoping
Firmenwatch puts the portfolio key in the URL path (/portfolios/{sourceKey}/...) and the review-case id in /actions/{id}, so a rule can pin your agent to the register read operations or to one portfolio's sync. You choose the operations it may call, so write operations like committing a sync or changing a review case are not included unless you add them.
Credential isolation
Your Firmenwatch token 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 Swiss company by name' or 'reconcile a portfolio of UIDs', and Jentic returns the matching Firmenwatch 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 Firmenwatch API through Jentic.
What authentication does the Firmenwatch API use?
The Firmenwatch API authenticates with a bearer token sent in the Authorization header, per its OpenAPI spec. A couple of endpoints, the public UID resolver and the health check, need no credential. Through Jentic the token is stored encrypted by your own Jentic One instance and injected at call time, so it never lands in the agent's context.
Is there a Firmenwatch MCP server?
You don't need an MCP server to give your agent the Firmenwatch API. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls the register search, lookup, and reconcile operations on demand, without a separate server's tool definitions loaded into its context.
Can I limit what my agent is allowed to do with the Firmenwatch API?
Yes. Write a rule that allows only the register read operations, such as searching companies and reading officers and events, so the agent can look up Swiss entities but cannot start a portfolio sync or change a review case, and every call it makes is logged.
Can I match company names to UIDs with the Firmenwatch API?
Yes. The match endpoint takes up to 500 company names without known UIDs and returns a safe mapping to their register identities, and the reconcile endpoint checks up to 500 UIDs you already hold against the current register in one request.
What are the rate limits for the Firmenwatch API?
The OpenAPI spec does not specify rate limits. Check the vendor documentation at https://firmenwatch.ch for the current limits and batch sizes before running large reconciliation jobs.
How do I look up a Swiss company through Jentic?
Search Jentic for 'find a Swiss company by name', which returns the Firmenwatch search operation with its input schema, then follow up with the UID lookup to fetch the full record and officers. To run it on your own infrastructure, install Jentic One from its GitHub repo.
GET STARTED