DeutschlandGPT MCP integration for AI agents.
Connect AI agents to DeutschlandGPT through 3 structured actions, including list models, create chat completion, and create embeddings. Review authentication…
- 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 DeutschlandGPT integration exposes
The DeutschlandGPT Agent App exposes 3 provider-backed actions for ai work. Its current contract lets an authorized agent list text models enabled for the connected deutschlandgpt workspace, create a synchronous text chat completion through deutschlandgpt, and create embedding vectors for one or more text inputs through deutschlandgpt. 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 DeutschlandGPT account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real DeutschlandGPT capabilities.
Showing 3 of 3 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
list_modelsREADList text models enabled for the connected DeutschlandGPT workspace.
create_chat_completionWRITECreate a synchronous text chat completion through DeutschlandGPT.
INPUTS: model / messages / max_completion_tokens / temperature / stream
create_embeddingsWRITECreate embedding vectors for one or more text inputs through DeutschlandGPT.
INPUTS: model / input / dimensions / encoding_format / task_type
INPUT CONTRACTS
Know what the action needs before it runs.
create_chat_completion
modelREQUIRED- The model ID returned by list_models.
messagesREQUIRED- The ordered text conversation sent to the model.
max_completion_tokensOPTIONAL- The maximum number of generated tokens, including reasoning tokens.
temperatureOPTIONAL- The sampling temperature between 0 and 2.
streamOPTIONAL- Whether to stream the response. Connector actions only accept false or an omitted value.
create_embeddings
modelOPTIONAL- The embedding model identifier. Omit it to use the workspace default.
inputREQUIRED- Text or a list of texts to embed.
dimensionsOPTIONAL- The requested embedding vector length when supported by the model.
encoding_formatOPTIONAL- The representation used for embedding vectors.
task_typeOPTIONAL- A task-type hint for optimizing Gemini embedding models, such as SEMANTIC_SIMILARITY.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect List Models
List text models enabled for the connected DeutschlandGPT workspace. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
list_modelsControl Create Chat Completion
Create a synchronous text chat completion through DeutschlandGPT. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.
create_chat_completionVerify with Create Chat Completion
Create a synchronous text chat completion through DeutschlandGPT. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
create_chat_completionSAFETY BOUNDARY
Operate DeutschlandGPT with explicit limits
- Authorize DeutschlandGPT with API key and grant only the provider access required by the selected actions.
- 2 actions are change-capable by name. Confirm the target identity and material parameters before allowing a write.
- 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 DeutschlandGPT rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the DeutschlandGPT task completed successfully.
CONNECTION MODEL
API key
DeutschlandGPT Platform API key used as a Bearer token. Manage keys at https://dialog.deutschlandgpt.de/platform-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
- 1
- WRITE SIGNALS
- 2
- HIGH IMPACT
- 0
- REVIEW SIGNALS
- 0
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 DeutschlandGPT.