Official MCP RegistryListed
Synap
Open AI models through one OpenAI-compatible API: chat, live model list, prices and cost estimates.
First seen 2 Oct 2026. Evidence as of 5 Oct 2026.
4
Tools
From an anonymous probe
1
Source listings
Each with its own history
14
Recorded changes
Since first seen
Tools
| Tool | Description | Behaviour |
|---|---|---|
| synap_chat_completion | Send a conversation to a model on Synap, Linkrra's OpenAI-compatible inference API, and get the model's reply. Use this when you need text generated, code written or a question answered by one of the open models Synap serves. This is the only tool here that costs money: it bills prompt and completion tokens to the Synap API key supplied as the Authorization: Bearer header on the MCP connection. With no key it returns an error and nothing is spent; a key with no balance returns insufficient_credits. Call synap_estimate_cost first if the price matters. Returns the standard OpenAI chat.completion JSON (choices[0].message.content holds the reply, usage holds token counts). The call is not streamed and keeps no memory between calls — send the full message history each time. | Changes data |
| synap_estimate_cost | Work out what a chat completion would cost on Synap from token counts, using the live price list. Use this before synap_chat_completion when budget matters, or to compare models for a job. Free, read-only, needs no API key and runs no model. Returns {model, prompt_tokens, completion_tokens, prompt_usd, completion_usd, total_usd, pricing}. It is an estimate: the real charge uses the token counts the model reports afterwards. Auto-routing ids such as "synap-v1" have no fixed price and return an error saying so. | Read-only |
| synap_get_model | Return the complete catalogue record for one Synap model: pricing, context and output limits, supported parameters, quantisation, data-retention policy and readiness. Use this after synap_list_models when you need details the summary leaves out. Free, read-only and needs no API key. Returns the raw model object, or an error naming the id if Synap does not serve it. | Read-only |
| synap_list_models | List the models Synap serves right now, each with its price per million tokens, context window and what it is good at. Use this to choose a model id before calling synap_chat_completion, or to compare prices. Free, read-only, no API key needed, and safe to call repeatedly; the list is live, so models can appear or go between calls. Returns {"object":"list","count":N,"data":[{id,name,capability,tier,context_tokens,max_output_tokens,pricing,data_policy}]}; pricing is USD per million prompt and completion tokens and is absent for the auto-routing ids ("synap-v1"), which bill at the price of the model they route to. For every field of one model use synap_get_model. | Read-only |
Change history
- synap_list_models: title changed
- synap_list_models: input schema changed (+query)
- synap_list_models: description changed (+"the" +"serves right now, each with its price per million tokens, context window and what it is good at. Use this to choose a model id before calling synap_chat_completion, or to compare prices. Free, read-only, no API key needed, and safe to call repeatedly; the list is live, so models can appear or go between calls. Returns {"object":"list","count":N,"data":[{id,name,capability,tier,context_tokens,max_output_tokens,pricing,data_policy}]}; pricing is USD per million prompt and completion tokens and is absent for the auto-routing ids ("synap-v1"), which bill at the price of the model they route to. For every field of one model use synap_get_model." -"currently available on")
- synap_list_models: annotations changed
- synap_get_model: tool added
- synap_estimate_cost: tool added
- synap_chat_completion: title changed
- synap_chat_completion: input schema changed
- synap_chat_completion: description changed (+"Send a conversation to a model on" +"API, and get the model's reply. Use this when you need text generated, code written or" +"question answered by one of the open models Synap serves. This is")
- synap_chat_completion: annotations changed
- server instructions changed (+"Synap is Linkrra's OpenAI-compatible inference API for open models (https://synap.linkrra.com). synap_list_models, synap_get_model and synap_estimate_cost are free, read-only and need no key — use them to pick a model and price a job. synap_chat_completion runs a model and bills the Synap API key sent as the Authorization: Bearer header on this MCP connection; without a key it returns an error and spends nothing. Use model "synap-v1" to let Synap route to the cheapest model that can do the job.")
- Website changed from "https://pool.linkrra.com/ai" to "https://synap.linkrra.com" (registry)
- Name changed from "com.linkrra/synap" to "Synap" (registry)
- Description changed (registry)
| Source | Listing | First seen | Last seen | Versions |
|---|---|---|---|---|
| Official MCP Registry | com.linkrra/synap | 2 Oct 2026 | 5 Oct 2026 | 2 |