MCP Server
AccelsRouter ships a hosted MCP (Model Context Protocol) server — a single Streamable HTTP endpoint that exposes the gateway's catalog, pricing, account and chat abilities as tools your coding agent (Claude Code, Cursor, Codex, …) can call directly.
Instead of remembering model ids and prices, your agent asks the gateway directly.
Endpoint & auth
| Endpoint | https://router.accels.tech/mcp |
| Transport | Streamable HTTP (stateless) |
| Auth | Authorization: Bearer sk-... — your normal API key |
The MCP endpoint runs behind the same authentication as the API. A disabled, expired, or exhausted key is rejected, and every tool acts as that key — you only ever see the models, prices, credit and request history that key is entitled to.
Setup
Claude Code
claude mcp add --transport http accelsrouter https://router.accels.tech/mcp \
--header "Authorization: Bearer sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"Cursor / generic JSON clients
Add to the client's MCP config (e.g. Cursor's mcp.json):
{
"mcpServers": {
"accelsrouter": {
"url": "https://router.accels.tech/mcp",
"headers": {
"Authorization": "Bearer sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
}
}
}
}Any MCP client that speaks Streamable HTTP with a custom header works the same way — point it at the endpoint and pass the Authorization header.
Tools
Seven of the eight tools are read-only and free. Only send-message consumes credit.
| Tool | What it does | Key parameters | Cost |
|---|---|---|---|
ping | Health check; returns ok and server time | — | Free |
list-models | Models this key can call, with provider, supported endpoints and the effective price for this key | search, provider, endpoint, limit (≤500) | Free |
get-model | Full details for one model: description, tags, provider, endpoints, billing type, effective price | model | Free |
get-model-pricing | Effective price of one model for this key (USD per 1M tokens, or per call), including the group ratio | model | Free |
get-credits | This key's own cap and spend, plus the balance that funds it (a personal balance or an organization wallet); distributor admins also see the separate distributor wallet | — | Free |
get-generation | Cost, token counts and timing of one past request, by request id | request_id | Free |
list-daily-model-rankings | Most-used models on the platform over the last N days, by token volume | days (≤30), limit (≤50) | Free |
send-message | Send a chat message to a model and return the reply, token usage and cost | model, prompt or messages, system, max_tokens, temperature | Consumes credit |
send-message is dispatched internally through the normal /v1/chat/completions path, so model allow-lists, routing, rate limits and billing apply exactly as they would for a direct API call.
Request ids
send-message returns a request_id — the same id returned in the response headers of a direct API call. Pass it to get-generation to read the final billed cost, token counts and latency once the call is recorded.
Distributor tools
If you're a distributor (reseller) admin, the server exposes an extra set of read-only tools for running your distribution business. They appear only when you call with one of your own distributor keys — a personal key, or a key in your distributor workspace. Ordinary users and your customers' keys never see them. All are free; anything that moves money or changes a customer's offer stays in the console behind its own 2FA.
| Tool | What it does | Key parameters |
|---|---|---|
reseller-summary | Your distributor account at a glance: wallet balance, price group, wholesale discounts and customer count | — |
reseller-customers | Your customers with status, wallet balance, net credit you've allocated and how many models each may use | — |
reseller-usage | Usage and profit over the last N days — standard price, what customers paid you, your cost and margin — broken down by customer, model and member | days (≤90), customer_id (optional) |
reseller-customer-logs | Recent call records of one customer: model, tokens, standard price, what they paid, latency and request id | customer_id, days (≤90), limit (≤100) |
reseller-customer-offer | The models one customer may call and the per-model-series discounts you granted them | customer_id |
reseller-ledger | Your distributor wallet ledger: purchases, allocations to customers and revocations, newest first | limit (≤100) |
Typical workflow
A coding agent connected to the MCP server can, for example:
list-models— discover what models are available to the keyget-model-pricing— compare the effective price of two candidate modelsget-credits— check there's enough balancesend-message— run a quick test prompt against the chosen modelget-generation— confirm the exact cost of that call
All of this happens without leaving the agent or hard-coding model ids and prices.
Notes
- Stateless — every request is a self-contained session; nothing is stored between calls.
- Same billing as the API — credit, quotas and rate limits are shared with your key's normal API usage; the MCP server is just another way in.
- Least privilege — issue a dedicated key (optionally quota-capped) for agents that only need catalog/pricing lookups. See API Keys.