Synap MCP
An MCP server providing OpenAI-compatible LLM inference for AI agents. It allows agents to list available models, get model details, estimate costs, and perform chat completions. It supports pay-per-call billing via USDC (x402) or API keys, with self-hosted open models and brokered frontier models.
Endpoint and access
No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.
https://synap402.com/mcpWhat its tools do
4 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.
Read-only (3)
Can change data (1)
Checks and signals
Each line is separate evidence, not a trust score.
- Passed Endpoint answered the live check ·
- Passed Official MCP Registry namespace is tied to synap402.com ·
- Passed Endpoint is on the registry namespace domain ·
- Availability 1 of 1 checks passed in 30 days
What you can do with it
- List available LLM models and their live prices
- Estimate the cost of a chat completion before sending
- Execute chat completions using OpenAI-compatible API
- Discover models and pay per call autonomously
Source and maintenance
Protocol and capabilities
- Server
- synap 1.2.0
- MCP protocol negotiated in check
- 2025-11-25
- Tools
- 4 advertised
- Resources
- Not advertised
- Resource templates
- Not advertised
- Prompts
- Not advertised
{
"tools": {}
}Server-provided instructions
Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.
Tools
4 advertised
synap_chat_completion — Run a chat completion on Synap
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.
{
"type": "object",
"required": [
"model",
"messages"
],
"properties": {
"model": {
"type": "string",
"description": "Model id exactly as returned by synap_list_models, e.g. \"qwen3-coder-30b\". Use \"synap-v1\" to let Synap pick the cheapest model that can handle the request."
},
"messages": {
"type": "array",
"items": {
"type": "object",
"required": [
"role",
"content"
],
"properties": {
"role": {
"enum": [
"system",
"user",
"assistant"
],
"type": "string",
"description": "Who wrote the message: system (instructions), user, or assistant (an earlier model reply)."
},
"content": {
"type": "string",
"description": "The message text."
}
}
},
"minItems": 1,
"description": "The conversation so far, oldest first. The last message is normally the user turn to answer."
},
"max_tokens": {
"type": "integer",
"minimum": 1,
"description": "Upper limit on tokens generated in the reply. Omit to use the model default; lower it to cap cost."
},
"temperature": {
"type": "number",
"maximum": 2,
"minimum": 0,
"description": "Sampling randomness, 0 to 2. Lower is more deterministic. Omit to use the model default."
}
}
}{
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}synap_list_models — List Synap models and prices
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.
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Optional case-insensitive filter matched against model id, name and capability, e.g. \"coder\", \"qwen\" or \"vision\". Omit to list everything."
}
}
}{
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}synap_get_model — Get one Synap model in full
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.
{
"type": "object",
"required": [
"model"
],
"properties": {
"model": {
"type": "string",
"description": "Model id exactly as returned by synap_list_models."
}
}
}{
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}synap_estimate_cost — Estimate the cost of a Synap call
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.
{
"type": "object",
"required": [
"model",
"prompt_tokens"
],
"properties": {
"model": {
"type": "string",
"description": "Model id exactly as returned by synap_list_models."
},
"prompt_tokens": {
"type": "integer",
"minimum": 0,
"description": "Tokens you will send (system + conversation). Roughly 4 characters of English per token."
},
"completion_tokens": {
"type": "integer",
"minimum": 0,
"description": "Tokens you expect back. Use your max_tokens for a worst case. Defaults to 0."
}
}
}{
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}Prompts
Not advertised
Resources
Not advertised
90-day uptime
A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.
- 2026-11-09: 2 of 2 checks answered
- 2026-11-10: 1 of 1 checks answered
30-day availability
Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.
- Successful checks
- 1 of 1 (100%)
- Average latency
- 749 ms
- 95th percentile latency
- 749 ms
Maintenance history
Public check and source-refresh events. Editorial and ownership records remain private.
- · probe · passed · 749 ms · metadata changed · 4 tool(s)
Connect from your client
Each snippet registers the same endpoint; pick the client you use.
Claude Code
claude mcp add --transport http synap-mcp https://synap402.com/mcpCodex
codex mcp add synap-mcp --url https://synap402.com/mcpCursor
{
"mcpServers": {
"synap-mcp": {
"url": "https://synap402.com/mcp"
}
}
}Cline
{
"mcpServers": {
"synap-mcp": {
"type": "streamableHttp",
"url": "https://synap402.com/mcp",
"disabled": false
}
}
}VS Code
{
"servers": {
"synap-mcp": {
"type": "http",
"url": "https://synap402.com/mcp"
}
}
}Gemini CLI
gemini mcp add --transport http synap-mcp https://synap402.com/mcpClaude Desktop
https://synap402.com/mcpWindsurf
{
"mcpServers": {
"synap-mcp": {
"serverUrl": "https://synap402.com/mcp"
}
}
}Let your agent find its tools
Find servers like Synap MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.
Other ai and machine learning servers
Do you run Synap MCP?
Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.