Synap MCP server
com.linkrra/synaplinkrra.comstreamable-httpv1.2.0Scanned
Open AI models through one OpenAI-compatible API: chat, live model list, prices and cost estimates.
4 tools: 1 do something that can't be undone, 1 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 1
- Can send data out · 1
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Synap MCP server can do
The Synap MCP server is published by linkrra.com, a domain the MCP Registry verified. It has 4 tools. It can do things that cannot be undone, such as sending, paying or publishing (synap_chat_completion) and create or change data (1 tool: synap_estimate_cost), but cannot delete data. 2 tools only read.
1 tool brings in text other people can write (synap_chat_completion); 1 tool can send data out of your system (synap_chat_completion).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 10, 2026, version 1.2.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
4 tools
Can't be undone 1Claude Code: ask
synap_chat_completionSend a conversation to a model on Synap, Linkrra's OpenAI-compatible inference API, and get the model's reply.Reads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "send": a word for sending, and what is sent cannot be taken back.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe description's first verb is "send": it sends or publishes something to other people.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Changes things 1Claude Code: ask
synap_estimate_costWork out what a chat completion would cost on Synap from token counts, using the live price list.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 2Show 2 read-only tools
synap_get_modelReturn the complete catalogue record for one Synap model: pricing, context and output limits, supported parameters, quantisation, data-retention policy and readiness.No findings
Why it is in this group
- The name "synap_get_model" says "get": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
synap_list_modelsList the models Synap serves right now, each with its price per million tokens, context window and what it is good at.No findings
Why it is in this group
- The name "synap_list_models" says "list": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:41 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 2
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 2 tools that change things (1 irreversible, 1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://pool.linkrra.com/mcp: tools/list returned 4 tools to an anonymous client, including synap_chat_completion (irreversible), synap_estimate_cost (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http synap https://pool.linkrra.com/mcpclaude mcp add --transport http synap https://pool.linkrra.com/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__synap__synap_list_models",
"mcp__synap__synap_get_model"
],
"ask": [
"mcp__synap__synap_chat_completion",
"mcp__synap__synap_estimate_cost"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as synap. Review it before you use it.
Capability tags behind 1 rule
- mcp__synap__synap_chat_completion untrusted-input, outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.linkrra/synap/verify?hash=32b05abebd6c5daf34731ecb49c6982d437e3b5691086d96600818a027860636" | jq -e '.changed == false'Pinned hash 32b05abebd6c, from Nov 10, 2026, 20:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.linkrra/synap/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.linkrra/synap)Source: MCP Registry · repository. Synced Oct 21, 2026, 17:58 UTC.
Synap MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Synap MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, 2 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Synap MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Synap MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: synap_chat_completion.
What tools does the Synap MCP server have?
- 4 tools: 1 irreversible, 1 write, 2 read. synap_chat_completion, synap_estimate_cost, synap_list_models and synap_get_model.
Does the Synap MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Synap MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): synap_chat_completion.
Has the Synap MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 10, 2026.