TokenZero MCP server
io.github.tokenzero-ai/tokenzerotokenzero-aistreamable-httpv0.2.2Scanned
LLM cost optimization gateway, repo token-waste auditor & model arbitrage MCP server.
6 tools: 6 change things.
- Reads private data · 0
- Reads text others write · 1
- Can send data out · 1
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
6 tools here change things. Govern them.
- 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 TokenZero MCP server can do
The TokenZero MCP server is published by the GitHub account tokenzero-ai. It has 6 tools. It can create or change data (6 tools: try_tokenzero, audit_repo_token_waste, optimize_prompt_payload, calculate_model_arbitrage and 2 more), but cannot delete data. None of its tools only reads.
1 tool brings in text other people can write (audit_repo_token_waste); 1 tool can send data out of your system (optimize_prompt_payload).
The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 9, 2026, version 0.2.2.
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.
6 tools
Changes things 6Claude Code: ask
audit_repo_token_wasteNo API key needed.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it No API key needed. Static-analyze a public GitHub repo (e.g. {"repo": "owner/name"}) or a set of source files for LLM token waste: uncached static prompts, frontier models on extraction tasks, hot loops, non-deterministic repeat calls, and prompt-caching mis-integration (caching gated on model names, volatile values in the system prompt, random ids in history, wrong-provider cache markers, misplaced breakpoints, cost math that ignores cached tokens). Returns findings with fixes and an estimated recoverable percentage.
Annotations the server declares
- title: Audit a repo for LLM token waste
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
calculate_model_arbitrageNo API key needed; only `model` is required (e.g.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 No API key needed; only `model` is required (e.g. {"model": "gpt-6.1-sol"}, defaults 2,000 tokens in and 400 out). Price a workload at list prices across models: cost per request and per month for the requested model, its cheaper sibling, and the effect of prompt caching. The result names the pricing table version it used.
Annotations the server declares
- title: Price a workload across models
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
optimize_prompt_payloadNo API key needed.Can send data outNo 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.
What it can reach
- outboundThe input takes a URL (input.endpoint): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it No API key needed. Rewrite an OpenAI Chat/Responses or Anthropic Messages request body so its static prefix is provider-cacheable (Anthropic cache_control breakpoints, OpenAI prompt_cache_key). Returns the optimized body, what changed, the token profile and the projected per-request saving. Never changes the tokens the model sees.
Annotations the server declares
- title: Make a request body cache-friendly
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
provision_workspaceCreate a TokenZero workspace and key with no form.No findings
Why it is in this group
- The description's first verb is "create": a word for a change.
Description, as the server wrote it Create a TokenZero workspace and key with no form. Returns the key once, the base URLs that route through it (OPENAI_BASE_URL / ANTHROPIC_BASE_URL), the one-click dashboard link and the badge URL. Free up to the monthly free tier; nothing is billed.
Annotations the server declares
- title: Create a free TokenZero workspace
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
try_tokenzeroCall this first: no API key, no signup, no setup.1 finding
Why it is in this group
- The description's first verb is "call": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "try_tokenzero" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The description's first verb is "call": a word for a change.
Description, as the server wrote it Call this first: no API key, no signup, no setup. Shows what TokenZero would do to one of your LLM calls: it runs the four savings engines (prompt-cache formatting, edge cache, cascade advice, signed receipt) on a sample or your own prompt and model, and returns the list-price saving, the signed receipt and a copy-paste keyless curl that makes a real call on a free model. Pass {} for the default, or {"model": "gpt-6.1-sol", "system": "...", "prompt": "..."}.
Annotations the server declares
- title: Try TokenZero (no key needed)
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
workspace_metricsLive value scorecard for a TokenZero workspace: hard savings and net ROI per window, the four engines' contribution, speed, parity, availability and privacy posture, per-model brea…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 Live value scorecard for a TokenZero workspace: hard savings and net ROI per window, the four engines' contribution, speed, parity, availability and privacy posture, per-model breakdown and one-click recommendations. Needs the workspace key (tz_live_…); pass demo: true for a labelled sample.
Annotations the server declares
- title: Read a workspace savings scorecard
- 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 17, 2026, 15:24 UTC, unchanged since Nov 3, 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
- 6
- 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
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 6 tools that change things (6 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://tokenzero.sh/mcp: tools/list returned 6 tools to an anonymous client, including try_tokenzero (write), audit_repo_token_waste (write), optimize_prompt_payload (write), calculate_model_arbitrage (write), provision_workspace (write) and 1 more
Posture changes
- Nov 3, 2026
- Tools that change things, listed without credentials: 5 to 6
Findings
Matches of fixed checks, with the text they matched.
- Warntry_tokenzero
The server marks "try_tokenzero" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The description's first verb is "call": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools1 added, 5 changed.+1 added~5 changedView diff
- Added:try_tokenzeroChanges things
- Changed:audit_repo_token_wasteChanges thingstitledescriptionannotations
- Changed:calculate_model_arbitrageChanges thingstitledescriptioninputSchemaannotations
- Changed:optimize_prompt_payloadChanges thingstitledescriptionannotations
- Changed:provision_workspaceChanges thingstitleannotations
- Changed:workspace_metricsChanges thingstitleannotations
PostureRemote posture changed. Tools that change things, listed without credentials: 5 -> 6.View diff
- Tools that change things, listed without credentials: 5 to 6
Install
Pinned to version 0.2.2. Values in angle brackets are yours to fill in.
claude mcp add --transport http tokenzero https://tokenzero.sh/mcpclaude mcp add --transport http tokenzero https://tokenzero.sh/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": [],
"ask": [
"mcp__tokenzero__try_tokenzero",
"mcp__tokenzero__audit_repo_token_waste",
"mcp__tokenzero__optimize_prompt_payload",
"mcp__tokenzero__calculate_model_arbitrage",
"mcp__tokenzero__provision_workspace",
"mcp__tokenzero__workspace_metrics"
],
"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 tokenzero. Review it before you use it.
Capability tags behind 2 rules
- mcp__tokenzero__audit_repo_token_waste untrusted-input
- mcp__tokenzero__optimize_prompt_payload 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/io.github.tokenzero-ai/tokenzero/verify?hash=3ee24b26fdb193e21e4cbac0ade618f86ee87509edbf95a14c242fd6d5f9e4b3" | jq -e '.changed == false'Pinned hash 3ee24b26fdb1, from Nov 9, 2026, 08:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.tokenzero-ai/tokenzero/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.tokenzero-ai/tokenzero)Source: MCP Registry · repository. Synced Oct 26, 2026, 07:17 UTC.
TokenZero MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the TokenZero MCP server safe?
- No scan can promise that. What its definitions show: 6 tools, 6 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the TokenZero MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the TokenZero MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the TokenZero MCP server have?
- 6 tools: 6 write. try_tokenzero, audit_repo_token_waste, optimize_prompt_payload, calculate_model_arbitrage, provision_workspace and workspace_metrics.
Does the TokenZero MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the TokenZero 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): optimize_prompt_payload.
Has the TokenZero MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 9, 2026. Every change is on this page and in its Atom feed.