FreeToken — LLM API discovery
by freetoken.link · remote · no sign-in to list tools · v1.0.0 · published by link.freetoken
LLM API discovery: access conditions, dated costs, sampled checks and keyless configs. Read-only.
6 tools: 2 change things and 4 only read.
Scanned Oct 21, 2026
- Deletes or cancels0Claude Code: deny
- Can't be undone0Claude Code: ask
- Changes things2Claude Code: ask: see these tools
- Only reads4Claude Code: allow: see these tools
No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.
claude mcp add --transport http catalog https://freetoken.link/mcpTools
Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.
6 tools
Changes things 2Claude Code: ask
estimate_costEstimate USD cost for ONE listed priceId and its exact billing scenario.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 Estimate USD cost for ONE listed priceId and its exact billing scenario. inputMillion/outputMillion are millions of tokens, not individual tokens. Not a live quote, free quota calculation, or charge.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
export_keyless_configRender a keyless config for 1–5 exact catalog providerSlug/modelSlug pairs.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 Render a keyless config for 1–5 exact catalog providerSlug/modelSlug pairs. Only environment variable references are returned. No keys, prompts, network calls, or file writes. Review compatibility before using.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 4Claude Code: allow
get_provider_guideRead official application links, payment/identity conditions and existing application steps for a published provider.No findings
Why it is in this group
- The name "get_provider_guide" says "get": a word for reading.
Description, as the server wrote it Read official application links, payment/identity conditions and existing application steps for a published provider. No signup or key generation is performed.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_route_statusRead existing sampled checks for public catalog routes.No findings
Why it is in this group
- The name "get_route_status" says "get": a word for reading.
Description, as the server wrote it Read existing sampled checks for public catalog routes. No new checks run. Missing/stale evidence must not be interpreted as uptime or an outage. provider/model use catalog slugs.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_price_referencesList dated price reference IDs and billing scenarios for estimate_cost.No findings
Why it is in this group
- The name "list_price_references" says "list": a word for reading.
Description, as the server wrote it List dated price reference IDs and billing scenarios for estimate_cost. This is a limited reference set, not complete market coverage or live quotes.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_modelsFilter the published catalog (substring search, not a benchmark or guarantee of free access).No findings
Why it is in this group
- The name "search_models" says "search": a word for reading.
Description, as the server wrote it Filter the published catalog (substring search, not a benchmark or guarantee of free access). Returns exact provider/model slugs for subsequent tools, conditions, dates and source links.
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 or untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- 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 Oct 22, 2026, 15:10 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
- none
- RFC 9728 protected resource metadata
- none
- Authorization servers
- none
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://freetoken.link/mcp: tools/list returned 6 tools to an anonymous client, including estimate_cost (write), export_keyless_config (write)
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http catalog https://freetoken.link/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__catalog__search_models",
"mcp__catalog__get_provider_guide",
"mcp__catalog__list_price_references",
"mcp__catalog__get_route_status"
],
"ask": [
"mcp__catalog__estimate_cost",
"mcp__catalog__export_keyless_config"
],
"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 catalog. Review it before you use it.