Kourier
Server Details
Discover flat-rate DeepSeek plans, model limits, API-key instructions, and coding-client setup.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- kourierai/mcp
- GitHub Stars
- 0
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 8 tools
Most tools have clearly distinct purposes: the onboarding flow (create_checkout_link, complete_onboarding, get_onboarding_status) is step-distinguished, and informational tools (get_pricing, get_models) are separate. The three 'instructions/info' tools (get_api_key_instructions, get_setup_instructions, get_pricing) have some conceptual overlap and could momentarily confuse selection, but descriptions clarify their boundaries.
Every tool follows a clean verb_noun snake_case pattern: complete_onboarding, create_checkout_link, get_api_key_instructions, get_models, get_onboarding_status, get_pricing, get_setup_instructions, submit_feedback. The 'get_' prefix is used consistently for read operations. No convention mixing.
Eight tools is well-scoped for an onboarding/entitlement server. Each tool covers a discrete step or information need (link creation, status, key issuance, pricing, models, setup, feedback) without redundancy. No filler or missing obvious siblings.
The surface covers the full onboarding lifecycle (create link, poll status, issue key) plus setup, pricing, model info, and feedback — a coherent end-to-end flow. Minor gaps exist, such as no explicit key revocation or account/billing-state query, but these are outside the core onboarding scope and workable.
Publisher details
- Operator
- Kourier AI Inc
- Operator website
- https://kourier.sh/
- Vendor relationship
- First-party
- Documentation
- https://github.com/kourierai/mcp · Publisher source
- Privacy policy
- Not provided
- Trust center
- Not available
- Restrictions
- Provides methods to onboard onto paid kourier inference plans and onboard agents consumption of kourier
Available Tools
8 toolscomplete_onboardingExchange approved onboarding onceAInspect
Deliver a dedicated revocable inference key exactly once after human approval and active entitlement. Never retry after issuance or ambiguous delivery; check status instead. Keep the key private and configure the client only with user approval.
Inputs: onboarding_token (required).
create_checkout_linkStart human-approved onboardingAInspect
Create a verified sign-in, recurring Starter/Pro plan and explicit agent access approval link. Show only onboarding_url and user_code to the human; keep the token private. This does not itself charge or issue a key.
Inputs: plan (required), client_name (required), harness.
get_api_key_instructionsGet an API keyARead-onlyIdempotentInspect
How a person or an agent obtains a Kourier API key: dashboard sign-up, agent sign-in (auth.md), or OAuth with PKCE.
Inputs: no named parameters.
get_modelsModels and limitsBRead-onlyIdempotentInspect
The model Kourier serves, its API model string, and context limits.
Inputs: no named parameters.
get_onboarding_statusCheck onboarding approvalARead-onlyIdempotentInspect
Check approval and signed-webhook-backed entitlement, without identity or secrets. Poll every 5 seconds; complete only when ready. Stop on issued, denied or expired.
Inputs: onboarding_token (required).
get_pricingPlans and pricingARead-onlyIdempotentInspect
Kourier's plans, monthly prices, concurrency limits, and what has no usage cap.
Inputs: no named parameters.
get_setup_instructionsTool setupCRead-onlyIdempotentInspect
Configuration for using Kourier from Oh My Pi, Claude Code, Codex CLI, or any OpenAI-compatible client.
Inputs: harness.
submit_feedbackSubmit feedback or an error reportAInspect
Send feedback or report a Kourier error, attributed to your account. Requires your Kourier API key in the MCP connection's Authorization: Bearer header, never in tool arguments. Submit only what the user wants to share; exclude API keys, tokens, passwords, personal data, and private code or logs. Include a request_id when available to help investigation.
Inputs: kind (required), message (required), request_id, client_name.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Find the AI coding/app-builder plan that fits your usage: limits, prices and plan-fit picks.
Find the AI coding/app-builder plan that fits your usage: limits, prices and plan-fit picks.
Ask Claude, GPT, Grok, GLM, Kimi or DeepSeek from your client; token price plus a $0.001 call fee.
Ask Claude, GPT, Grok, GLM, Kimi or DeepSeek from your client; token price plus a $0.001 call fee.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides code generation and completion capabilities using the DeepSeek API, with support for tool chaining and cost optimization.5ISC
- AlicenseNot gradedqualityAmaintenanceEnables dispatching tasks from coding hosts such as Claude Code, Codex, Antigravity and Grok to DeepSeek Harness agents that appear as native subagents with live progress, tier/effort policy, escalation, and workspace guardrails. Also lends text-only harnesses vision and image generation through DeepSeek VL models or existing CLIs.354 npmMIT
- AlicenseAqualityCmaintenanceEnables using DeepSeek models as a small, cheap supervised worker from any MCP-compatible client, providing fast flash and deep reasoning tools for bounded tasks.256MIT
- AlicenseNot gradedqualityBmaintenanceEnables querying DeepSeek-Flash with configurable chain-of-thought effort and running autonomous code tasks that plan a spec, edit files, run tests, and self-review the resulting diff. Also provides adversarial code auditing, API health and latency checks, plus workspace, command-blacklist, and Git branch safety guardrails.1MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.