TokenLab MCP Server
OpenAPI-generated Model Context Protocol server for TokenLab public model discovery, pricing, native LLM endpoints, typed decisions, multimodal generation, async tasks, files, embeddings, rerank, translation, resources, prompts, and the broader developer API.
It exposes public catalog tools for agents that need to choose models, inspect supported request formats, or compare pricing before calling TokenLab APIs. Credentialed tools cover text inference, image generation and editing, video, music, 3D, async task polling, embeddings, rerank, typed decisions, and text translation.
The checked-in generated/tools.json manifest is generated from TokenLab's public OpenAPI document plus the small MCP-only overlay in contract/mcp-overlay.json. Version 0.6.30 generates 87 endpoint tools; with the two MCP-only composite discovery tools, the full profile returns 89 tools from tools/list.
| Profile | Endpoint tools | Total registered tools | Model-facing schema | Coverage |
|---|
catalog | 4 | 6 | Exact | Public model discovery and pricing only; no API key required |
core (default) | 30 | 32 | Portable | Catalog and pricing; Chat Completions, Responses, Anthropic Messages, Gemini generateContent; System One typed decisions; images, video, music, 3D, speech and transcription; async tasks; files; embeddings, rerank, and translation |
full | 87 | 89 | Portable | Every allowlisted developer API operation in the checked-in OpenAPI snapshot, including core plus response lifecycle, batches, worlds, and native model discovery |
The total registered count is the number returned by tools/list. All profiles include compare_models and get_api_overview, producing totals of 6, 32, and 89 tools. Realtime and streaming-only operations are excluded because stdio MCP tool calls return one final result. API operations that accept stream fix it internally to false without exposing a boolean const to provider adapters, and the Gemini query-string API key is intentionally hidden from tool arguments. create_gemini_content exposes the camelCase Gemini fields (systemInstruction, generationConfig, safetySettings, toolConfig, cachedContent) and hides their snake_case proto spellings, which the API accepts as aliases.
The portable projection keeps every top-level argument but bounds deeply nested model-facing shapes. The server still validates calls against the complete generated OpenAPI schema before issuing an API request. Compatibility budgets keep core at no more than 60 KB and depth 8, and full at no more than 115 KB and depth 8 for the complete tools/list response. Tests also run the full profile through the Google AI SDK version used by the observed OpenCode/Gemini failure and keep its function declarations within 90 KB.
Set TOKENLAB_MCP_TOOL_PROFILE=catalog for the smallest public-only tool list or TOKENLAB_MCP_TOOL_PROFILE=full for the broad developer API. Set TOKENLAB_MCP_SCHEMA_MODE=exact only when a client needs the complete nested JSON Schema and can accept its larger/deeper tool payload. Use strict for providers that require every property to be listed in required and every object to set additionalProperties: false; complex top-level arguments are represented as JSON-encoded strings and decoded before canonical validation. Canonical tool names, descriptions, input JSON Schemas, HTTP bindings, content types, auth requirements, and task behavior can be inspected in generated/tools.json.
The smaller generated/public-contract.json is the machine-readable projection used by TokenLab's website and other public consumers. It contains package identity, profile counts, core tool layers, resources, prompts, and source hashes without copying all endpoint schemas.
Native MCP Features
- JSON tool responses include
structuredContent while retaining serialized text for older clients.
- HTTP errors retain the original response text (up to 4,000 characters), including public correction hints, alongside structured status, request ID and retry timing. Only the request ID and retry headers are exposed; failed generation requests are never submitted again automatically.
- Generated tools expose human-readable titles, standard read-only/destructive/idempotent/open-world annotations, and response request IDs when available.
- Tool schemas are published and validated directly as JSON Schema. The runtime does not round-trip generated tool schemas through Zod;
exact mode is byte-shape equivalent to the generated canonical schema.
- Three resources expose the live API overview, the package's OpenAPI snapshot, and the compact MCP public contract.
choose_tokenlab_model and build_tokenlab_request prompts guide agents to use live model truth and preserve native endpoint shapes.- Server instructions tell clients to confirm billable or destructive operations and treat external model/API output as untrusted content.
Run
Install from npm:
npx -y @tokenlabai/mcp-server
Agent-assisted installers can follow llms-install.md for a credential-safe setup and verification flow.
Run in Docker:
docker build -t tokenlab-mcp-server .
docker run --rm -i tokenlab-mcp-server
Add -e TOKENLAB_API_KEY when using credentialed API tools. Public catalog tools do not require a key.
Claude Desktop style config:
{
"mcpServers": {
"tokenlab-model-catalog": {
"command": "npx",
"args": ["-y", "@tokenlabai/mcp-server"],
"env": {
"TOKENLAB_API_BASE": "https://api.tokenlab.sh"
}
}
}
}
No TokenLab API key is required for public catalog and pricing operations. Set TOKENLAB_API_KEY when credentialed tools should call TokenLab APIs. Generated tools preserve the OpenAPI request shape for OpenAI-compatible and native endpoints instead of flattening them into a shared prompt format.
Multipart operations accept local file paths. Small image and audio responses are returned as native MCP content; larger or other binary responses are written to TOKENLAB_ARTIFACT_DIR and returned as a path with MIME type and byte count.
Video, music, and 3D creation tools always return an async task. Image generation and editing may return a completed result or an async task depending on the selected model and request.
Media tools preserve the complete TokenLab API response under response and add a normalized delivery summary:
{
"delivery": {
"mode": "async",
"task_id": "ldtask_...",
"status": "pending",
"poll_url": "/v1/tasks/ldtask_...",
"terminal": false,
"next_tool": "get_task_status"
},
"response": {}
}
Use delivery.mode instead of assuming all image requests are synchronous. For async tasks, call get_task_status with { "id": delivery.task_id } until delivery.terminal is true. Completion is determined from status, not from an optional progress field.
Environment
TOKENLAB_API_BASE: optional, defaults to https://api.tokenlab.shTOKENLAB_API_KEY: optional; required for text inference, multimodal generation, async task, embedding, rerank, decision, and translation toolsTOKENLAB_MCP_TOOL_PROFILE: optional, catalog, core (default), or fullTOKENLAB_MCP_SCHEMA_MODE: optional, portable, exact, or strict; defaults to the selected profile's tested modeTOKENLAB_REQUEST_TIMEOUT_MS: optional request timeout in milliseconds, defaults to 120000TOKENLAB_MCP_MAX_FILE_BYTES: optional maximum local upload size per file, defaults to 104857600 (100 MiB)TOKENLAB_MCP_INLINE_BYTES: optional maximum binary/JSON response size returned inline, defaults to 2097152 (2 MiB)TOKENLAB_ARTIFACT_DIR: optional output directory for non-inline response artifacts, defaults to the OS temp directory under tokenlab-mcp
For Chat Completions image inputs, prefer byte-accurate data URLs such as data:image/png;base64,.... If an MCP caller labels a recognized PNG, JPEG, WebP, or GIF payload as application/octet-stream, the server corrects that generic MIME before forwarding. An unrecognized generic binary payload is rejected locally with a precise input error.
Contract Sync
The public OpenAPI document is the API contract source. The overlay contains only MCP-specific choices: profile exposure, stable tool aliases, secret omission, non-streaming constraints, content-type variants, async task semantics, and the compact public projection consumed by the website and docs gates.
npm run contract:source-check
npm run contract:check
npm run contract:sync
npm test
Always run git pull --ff-only before a manual contract sync. contract:check proves internal consistency only; contract:source-check proves freshness against the canonical source. The scheduled Sync TokenLab OpenAPI contract workflow runs the full write sequence and commits only the verified OpenAPI snapshot and generated manifest to main. A failed fetch, stale local branch, dirty generated output, generation error, schema compilation error, or test leaves the tracked contract unchanged.
This repository includes server.json for the official MCP Registry.
Release metadata:
- npm package:
@tokenlabai/mcp-server@0.6.30
- MCP registry name:
io.github.hedging8563/tokenlab
package.json.mcpName: io.github.hedging8563/tokenlab
For a new release:
- Bump the matching versions in
package.json, package-lock.json, and server.json.
- Push a matching tag such as
v0.6.0.
- The publish workflow tests and publishes npm through trusted publishing, then publishes the MCP Registry entry through GitHub Actions OIDC.
The same workflow can be run manually from main to republish only the current MCP Registry metadata. No npm or MCP Registry token is stored in GitHub.
Security
Use the catalog profile when no credentialed tools are needed. Keep TOKENLAB_API_KEY in the local MCP client's secret environment, enable human confirmation for billable and destructive calls, and review tool annotations before granting persistent approval. Do not send a TokenLab API key to an untrusted hosted MCP server.
Links
Webhook management
Use the full profile to configure workspace webhooks with list_webhooks, create_webhook, get_webhook, update_webhook, delete_webhook, rotate_webhook_secret, test_webhook and list_webhook_deliveries.
Set TOKENLAB_MANAGEMENT_TOKEN=mt-... separately from TOKENLAB_API_KEY=sk-.... Create the management token at Dashboard → API → Management Tokens. It authorizes management operations only within its workspace and is not limited to webhooks. The inference key cannot substitute for it; the whsec_... returned by creation/rotation is for receiver signature verification only. Keep all credentials out of tool arguments and prompts.
Webhook notifications avoid continuous task polling. On a polling fallback, stop on terminal status, 401/403/404 or retryable: false; back off on transient failures. See the complete webhook guide for payloads, signing, deduplication and delivery history.