OpenCage MCP integration for AI agents.
Connect AI agents to OpenCage through 3 structured actions, including geocode forward, geocode geojson, and geocode reverse. Review authentication, inputs, w…
- ACTION CONTRACTS
- 3
- AUTHENTICATION
- API key
- SOURCE STATUS
- Provider-backed
CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE
CAPABILITY PROFILE
What the OpenCage integration exposes
The OpenCage Agent App exposes 3 provider-backed actions for location and data work. Its current contract lets an authorized agent convert an address or place name into opencage geocoding results, return opencage geocoding results in geojson featurecollection format, and convert a latitude and longitude pair into opencage reverse geocoding results. These operations are called through Working Machines as typed capabilities rather than through browser navigation or copied UI steps.
A connection uses API key. Before execution, the agent can inspect the selected action, its required fields, declared scopes, and expected output contract. Provider credentials remain inside the Working Machines runtime; the calling agent receives the capability and its structured result, not the underlying secret.
For reliable operation, start with the narrowest action that satisfies the task, resolve stable provider identifiers before changing state, and validate the returned object or status after execution. Availability still depends on the connected OpenCage account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real OpenCage capabilities.
Showing 3 of 3 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
geocode_forwardREVIEWConvert an address or place name into OpenCage geocoding results.
INPUTS: q / limit / bounds / language / proximity
geocode_geojsonREVIEWReturn OpenCage geocoding results in GeoJSON FeatureCollection format.
INPUTS: q / limit / bounds / language / proximity
geocode_reverseREVIEWConvert a latitude and longitude pair into OpenCage reverse geocoding results.
INPUTS: q / language / roadinfo / abbrv / add_request
INPUT CONTRACTS
Know what the action needs before it runs.
geocode_forward
qREQUIRED- Address or free-form query string to geocode.
limitOPTIONAL- Maximum number of results to return, from 1 to 100.
boundsOPTIONAL- Bounding box bias formatted as west,south,east,north.
languageOPTIONAL- Preferred response language code.
proximityOPTIONAL- Bias results near a latitude,longitude point.
geocode_geojson
qREQUIRED- Address or free-form query string to geocode.
limitOPTIONAL- Maximum number of results to return, from 1 to 100.
boundsOPTIONAL- Bounding box bias formatted as west,south,east,north.
languageOPTIONAL- Preferred response language code.
proximityOPTIONAL- Bias results near a latitude,longitude point.
geocode_reverse
qREQUIRED- Latitude and longitude formatted as latitude,longitude.
languageOPTIONAL- Preferred response language code.
roadinfoOPTIONAL- Whether to include road information in the response.
abbrvOPTIONAL- Whether to abbreviate road and route names.
add_requestOPTIONAL- Whether to include the original request in the response.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Geocode Forward
Convert an address or place name into OpenCage geocoding results. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
geocode_forwardVerify with Geocode Geojson
Return OpenCage geocoding results in GeoJSON FeatureCollection format. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
geocode_geojsonSAFETY BOUNDARY
Operate OpenCage with explicit limits
- Authorize OpenCage with API key and grant only the provider access required by the selected actions.
- The current action names appear read-oriented, but returned OpenCage data may still be sensitive and should be minimized before it enters model context.
- Do not infer permission from catalog visibility. Workspace policy, connection identity, and upstream authorization still govern execution.
- No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in OpenCage rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the OpenCage task completed successfully.
CONNECTION MODEL
API key
OpenCage API key sent as the key query parameter. Find it in the Geocoding tab of your account dashboard: https://opencagedata.com/api.
Working Machines stores provider credentials behind the execution boundary. An agent can use an authorized connection identity, but catalog discovery alone does not reveal OAuth tokens, API keys, or provider secrets.
- READ SIGNALS
- 0
- WRITE SIGNALS
- 0
- HIGH IMPACT
- 0
- REVIEW SIGNALS
- 3
EVIDENCE AND AVAILABILITY
Provider reference
Action names, input fields, authentication types, and counts on this page are generated from the Working Machines provider catalog. Provider behavior, quotas, object semantics, account eligibility, and regional availability remain governed by OpenCage.