TokenSafe MCP server
dev.tokensafe/tokensafetokensafe.devstreamable-httpv4.3.3Scanned
Your AI agent is smart enough to code all day. Local firewall & zero-loss runtime.
13 tools: 1 can delete or cancel things, 4 change things and 8 only read.
- Reads private data · 2
- Reads text others write · 1
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here can delete or cancel things. 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 TokenSafe MCP server can do
The TokenSafe MCP server is published by tokensafe.dev, a domain the MCP Registry verified. It has 13 tools. It can delete or cancel things (1 tool: revoke_team_seat) and create or change data (4 tools: check_latest_version, distill_prompt, team_cache_store and generate_team_seat). 8 tools only read.
2 tools read private data (search_docs and preview_weekly_digest); 1 tool brings in text other people can write (preview_weekly_digest).
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 21, 2026, version 4.3.3.
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.
13 tools
Deletes or cancels 1Claude Code: deny
revoke_team_seatTeam owner: revokes a previously issued seat license.No findings
Why it is in this group
- The name "revoke_team_seat" says "revoke": a word for removing or ending something.
Description, as the server wrote it Team owner: revokes a previously issued seat license.
Changes things 4Claude Code: ask
check_latest_versionChecks the client version against the latest published tokensafe release.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.
Description, as the server wrote it Checks the client version against the latest published tokensafe release.
distill_promptManaged Cloud Distillation: compiles a verbose developer prompt into a dense TOCP S-expression server-side.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.
Description, as the server wrote it Managed Cloud Distillation: compiles a verbose developer prompt into a dense TOCP S-expression server-side. Requires Solo/Team license.
generate_team_seatTeam owner: provisions a seat license for a member email.No findings
Why it is in this group
- The name "generate_team_seat" says "generate": a word for a change.
Description, as the server wrote it Team owner: provisions a seat license for a member email.
team_cache_storeStores a distilled result in the shared team cache so teammates reuse it.No findings
Why it is in this group
- The name "team_cache_store" says "store": a word for a change.
Description, as the server wrote it Stores a distilled result in the shared team cache so teammates reuse it. Requires Team license.
Only reads 8Show 8 read-only tools
get_license_statusValidates the Bearer license key and returns tier, expiry and trial state.No findings
Why it is in this group
- The name "get_license_status" says "get": a word for reading.
Description, as the server wrote it Validates the Bearer license key and returns tier, expiry and trial state.
get_public_statsReturns aggregated public TokenSafe stats (total tokens saved, active teams).No findings
Why it is in this group
- The name "get_public_stats" says "get": a word for reading.
Description, as the server wrote it Returns aggregated public TokenSafe stats (total tokens saved, active teams). No auth.
get_setup_instructionsReturns exact MCP configuration snippets for a coding agent (cursor, claude_desktop, claude_code, codex, windsurf, antigravity, gemini_cli).No findings
Why it is in this group
- The name "get_setup_instructions" says "get": a word for reading.
Description, as the server wrote it Returns exact MCP configuration snippets for a coding agent (cursor, claude_desktop, claude_code, codex, windsurf, antigravity, gemini_cli).
get_team_metricsReturns the authenticated account's dashboard data: savings, telemetry stats, licenses and team seats.No findings
Why it is in this group
- The name "get_team_metrics" says "get": a word for reading.
Description, as the server wrote it Returns the authenticated account's dashboard data: savings, telemetry stats, licenses and team seats.
list_invoicesLists Stripe billing invoices for the authenticated account.No findings
Why it is in this group
- The name "list_invoices" says "list": a word for reading.
Description, as the server wrote it Lists Stripe billing invoices for the authenticated account.
preview_weekly_digestTeam owner: previews the weekly team stats digest (same data as the Friday email).Reads private dataReads text others writeNo findings
Why it is in this group
- The name "preview_weekly_digest" says "preview": a word for reading.
What it can reach
- private-dataThe description's first sentence says "email": it reads mail.
- untrusted-inputThe description's first sentence says "email": it reads inbound email, which other people can write.
Description, as the server wrote it Team owner: previews the weekly team stats digest (same data as the Friday email).
search_docsSearches the built-in TokenSafe knowledge base (features, install, tiers, privacy).Reads private dataNo findings
Why it is in this group
- The name "search_docs" says "search": a word for reading.
What it can reach
- private-dataThe name "search_docs" says "search" and "doc": it reads documents.
Description, as the server wrote it Searches the built-in TokenSafe knowledge base (features, install, tiers, privacy).
team_cache_lookupLooks up a shared team distillation cache entry by hash.No findings
Why it is in this group
- The name "team_cache_lookup" says "lookup": a word for reading.
Description, as the server wrote it Looks up a shared team distillation cache entry by hash. Requires Team license.
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 outbound.
- Reads private data2
- 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 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 Nov 19, 2026, 17:21 UTC, unchanged since Nov 12, 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
- 5
- 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 5 tools that change things (1 destructive, 4 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://api.tokensafe.dev/mcp: tools/list returned 13 tools to an anonymous client, including revoke_team_seat (destructive), check_latest_version (write), distill_prompt (write), team_cache_store (write), generate_team_seat (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 4.3.3. Values in angle brackets are yours to fill in.
claude mcp add --transport http tokensafe https://api.tokensafe.dev/mcpclaude mcp add --transport http tokensafe https://api.tokensafe.dev/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__tokensafe__get_public_stats",
"mcp__tokensafe__get_license_status",
"mcp__tokensafe__get_team_metrics",
"mcp__tokensafe__team_cache_lookup",
"mcp__tokensafe__list_invoices",
"mcp__tokensafe__get_setup_instructions",
"mcp__tokensafe__search_docs",
"mcp__tokensafe__preview_weekly_digest"
],
"ask": [
"mcp__tokensafe__check_latest_version",
"mcp__tokensafe__distill_prompt",
"mcp__tokensafe__team_cache_store",
"mcp__tokensafe__generate_team_seat"
],
"deny": [
"mcp__tokensafe__revoke_team_seat"
]
}
}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 tokensafe. Review it before you use it.
Capability tags behind 2 rules
- mcp__tokensafe__search_docs private-data
- mcp__tokensafe__preview_weekly_digest private-data, untrusted-input
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/dev.tokensafe/tokensafe/verify?hash=b9221a0edb800157a0ef477dd816082ca13f4ae0df13873e3398f93ae9d3a2e4" | jq -e '.changed == false'Pinned hash b9221a0edb80, from Nov 21, 2026, 15:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/dev.tokensafe/tokensafe/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/dev.tokensafe/tokensafe)Source: MCP Registry · repository. Synced Nov 21, 2026, 15:17 UTC.
TokenSafe MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the TokenSafe MCP server safe?
- No scan can promise that. What its definitions show: 13 tools, 5 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 TokenSafe MCP server delete data?
- Yes. 1 tool can delete, cancel or revoke something: revoke_team_seat.
Can the TokenSafe 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 TokenSafe MCP server have?
- 13 tools: 1 destructive, 4 write, 8 read. revoke_team_seat, check_latest_version, distill_prompt, team_cache_store, generate_team_seat, get_public_stats, get_license_status, get_team_metrics and 5 more.
Does the TokenSafe MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the TokenSafe MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the TokenSafe MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 21, 2026.