DeepSeek MCP integration for AI agents.

Connect AI agents to DeepSeek through 4 structured actions, including get user balance, create anthropic message, and create chat completion. Review authenti…

ACTION CONTRACTS
4
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 DeepSeek integration exposes

The DeepSeek Agent App exposes 4 provider-backed actions for ai work. Its current contract lets an authorized agent get the current deepseek account balance, create a deepseek message via the anthropic-compatible api, and create a deepseek chat completion via the openai-compatible api. 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 DeepSeek account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.

VERIFIED ACTION SAMPLE

Real DeepSeek capabilities.

Showing 4 of 4 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.

get_user_balanceREAD

Get the current DeepSeek account balance.

create_anthropic_messageWRITE

Create a DeepSeek message via the Anthropic-compatible API.

INPUTS: model / max_tokens / messages / stop_sequences / stream

create_chat_completionWRITE

Create a DeepSeek chat completion via the OpenAI-compatible API.

INPUTS: model / messages / frequency_penalty / logprobs / max_tokens

list_modelsREAD

List the available DeepSeek models.

INPUT CONTRACTS

Know what the action needs before it runs.

create_anthropic_message

modelREQUIRED
The DeepSeek model identifier.
max_tokensREQUIRED
The maximum number of tokens to generate.
messagesREQUIRED
The ordered conversation history to send to the model.
stop_sequencesOPTIONAL
Sequences that stop generation.
streamOPTIONAL
Whether to request a streaming response. This connector only accepts false or omission.

create_chat_completion

modelREQUIRED
The DeepSeek model identifier.
messagesREQUIRED
The ordered conversation history to send to the model.
frequency_penaltyOPTIONAL
The frequency penalty to apply to repeated tokens.
logprobsOPTIONAL
Whether to include token-level log probability details in the response.
max_tokensOPTIONAL
The maximum number of tokens to generate.

PROVIDER-SPECIFIC WORKFLOWS

Jobs this Agent App can support

Inspect Get User Balance

Get the current DeepSeek account balance. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.

get_user_balance

Control Create Anthropic Message

Create a DeepSeek message via the Anthropic-compatible API. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.

create_anthropic_message

Verify with List Models

List the available DeepSeek models. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.

list_models

SAFETY BOUNDARY

Operate DeepSeek with explicit limits

  • Authorize DeepSeek 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 DeepSeek rather than assuming unrestricted access.
  • After a call, inspect the structured result and execution record before reporting that the DeepSeek task completed successfully.

CONNECTION MODEL

API key

DeepSeek API key used for DeepSeek API requests. Create or manage keys at https://platform.deepseek.com/api_keys.

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
2
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 DeepSeek.

Official DeepSeek website

ONE CONNECTION. REAL WORK.

Give your agent software it can use.

Connect through MCP or explore the Agent App catalog and choose only the capabilities your workflow needs.

EXPLORE AGENT APPS