Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

TokenSafe

REMOTE · API.TOKENSAFE.DEV · 3 COMPONENTS

Your AI agent is smart enough to code all day. Local firewall & zero-loss runtime.

+4 this week 65 Trust /100

Last scanned (7 hours ago)

Scores higher than 46% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Developer Tools

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security57
Transport & Reachability100
Schema Quality & AI Usability68
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 626 tokens (~48/item across 13 items; 13 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management33
  • Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "revoke_team_seat" implies "revoke" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
  • Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
What we tested

Checks we ran (12)

  • TLS certificate
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (1)

These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Authorization in Endpoint SecurityAuthorisation not fully verified: no authorisation is required to call this server, and 13 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Nov 26 +1
    • Server version: 4.3.1 → 4.3.3 functional
  • 20 Nov 26 0
    • Server version: 4.2.13 → 4.3.1 functional
  • 19 Nov 26 +1
    • Server version: 4.2.12 → 4.2.13 functional
    • Server version: 4.2.11 → 4.2.12 functional
    • Server version: 4.2.10 → 4.2.11 functional
  • 18 Nov 26 0
    • Server version: 4.2.9 → 4.2.10 functional
    • Server version: 4.2.8 → 4.2.9 functional
    • Server version: 4.2.6 → 4.2.8 functional
    • Server version: 4.2.5 → 4.2.6 functional
    • Server version: 4.2.3 → 4.2.5 functional
  • 17 Nov 26 +1
    • Server version: 4.2.1 → 4.2.3 functional
    • Server version: 4.2.0 → 4.2.1 functional
    • Server version: 4.1.13 → 4.2.0 functional
    • Server version: 4.1.10 → 4.1.13 functional
    • Server version: 4.1.8 → 4.1.10 functional
    • Server version: 4.1.6 → 4.1.8 functional
  • 16 Nov 26 0
    • Transport: pass → fail ▼ security
    • Server version: 4.1.5 → 4.1.6 functional
    • Server version: 4.1.3 → 4.1.5 functional
    • Server version: 4.1.2 → 4.1.3 functional
    • Server version: 3.2.0 → 4.1.2 functional
  • 15 Nov 26 +1
    • Server version: 3.1.5 → 3.2.0 functional
  • 14 Nov 26 0
    • Server version: 3.1.4 → 3.1.5 functional
    • Server version: 3.1.2 → 3.1.4 functional
    • Server version: 3.1.1 → 3.1.2 functional
    • Server version: 3.1.0 → 3.1.1 functional
    • Server version: 3.0.0 → 3.1.0 functional
    • Server version: 2.9.0 → 3.0.0 functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://api.tokensafe.dev/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_256_GCM_SHA384 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=api.tokensafe.dev CN=YE2,O=Let's Encrypt,C=US 19 Nov 2026 17 Feb 2027 ECDSA 256 ECDSA-SHA384 53aa655b5715810357a6b419f128910dcbf
SANs: api.tokensafe.dev
CN=YE2,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 4df3b15dd6c0784c507cd37b58e6f115
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd
CN=ISRG Root X1,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 4 Jun 2015 4 Jun 2035 RSA 4096 SHA256-RSA 8210cfb0d240e3594463e0bb63828b00

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of api.tokensafe.dev. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
dev. DS published 60074 8 Verified
tokensafe.dev. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://api.tokensafe.dev/mcp Verified 200
http (plaintext) http://api.tokensafe.dev/mcp HTTPS enforced 301 https://api.tokensafe.dev/mcp
MCP tools · 13 exposed · ~570 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
check_latest_version ~59

Checks the client version against the latest published tokensafe release.

NameTypeReqDescription
client_versionstring–Your installed tokensafe version, e.g. 2.2.1
platformstring–Optional: darwin/linux/win32

No output schema declared.

No examples provided.

distill_prompt ~64

Managed Cloud Distillation: compiles a verbose developer prompt into a dense TOCP S-expression server-side. Requires Solo/Team license.

NameTypeReqDescription
context_hintstring–Optional: short context hint for the distiller
promptstringyesNatural language developer prompt

No output schema declared.

No examples provided.

generate_team_seat ~45

Team owner: provisions a seat license for a member email.

NameTypeReqDescription
member_emailstringyesMember email to invite
org_idstring–Optional organization id

No output schema declared.

No examples provided.

get_license_status ~25

Validates the Bearer license key and returns tier, expiry and trial state.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_public_stats ~26

Returns aggregated public TokenSafe stats (total tokens saved, active teams). No auth.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_setup_instructions ~60

Returns exact MCP configuration snippets for a coding agent (cursor, claude_desktop, claude_code, codex, windsurf, antigravity, gemini_cli).

NameTypeReqDescription
agentstring–Agent name; omit to list supported agents

No output schema declared.

No examples provided.

get_team_metrics ~27

Returns the authenticated account's dashboard data: savings, telemetry stats, licenses and team seats.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_invoices ~29

Lists Stripe billing invoices for the authenticated account.

NameTypeReqDescription
org_idstring–Optional organization id

No output schema declared.

No examples provided.

preview_weekly_digest ~27

Team owner: previews the weekly team stats digest (same data as the Friday email).

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

revoke_team_seat ~34

Team owner: revokes a previously issued seat license.

NameTypeReqDescription
license_keystringyesSeat license key to revoke

No output schema declared.

No examples provided.

search_docs ~40

Searches the built-in TokenSafe knowledge base (features, install, tiers, privacy).

NameTypeReqDescription
querystringyesFree-text query, min 2 chars

No output schema declared.

No examples provided.

team_cache_lookup ~52

Looks up a shared team distillation cache entry by hash. Requires Team license.

NameTypeReqDescription
hashstringyessha256 of the normalized prompt
typestring–Cache entry type, default PROMPT

No output schema declared.

No examples provided.

team_cache_store ~82

Stores a distilled result in the shared team cache so teammates reuse it. Requires Team license.

NameTypeReqDescription
hashstringyessha256 of the normalized prompt
tokens_savedinteger–Approximate tokens saved by this entry
typestring–Cache entry type, default PROMPT
valuestringyesDistilled TOCP S-expression

No output schema declared.

No examples provided.

Install

How do I install the TokenSafe MCP server?

TokenSafe is a hosted endpoint at https://api.tokensafe.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · api.tokensafe.dev

# add to Claude Code
claude mcp add --transport http dev-tokensafe-tokensafe 'https://api.tokensafe.dev/mcp'
Common questions

What is the TokenSafe MCP server?

TokenSafe is an MCP server listed in the public MCP registry as dev.tokensafe/tokensafe. Your AI agent is smart enough to code all day. Local firewall & zero-loss runtime. This page covers its hosted endpoint (https://api.tokensafe.dev/mcp).

Is the TokenSafe MCP server safe to use?

TokenSafe scores 65 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the TokenSafe MCP server expose?

TokenSafe exposes 13 tools: get_public_stats, check_latest_version, get_license_status, get_team_metrics, distill_prompt, and 8 more. Their descriptions and schemas cost roughly 570 tokens of context every time the server is loaded.

Does the TokenSafe MCP server require authentication?

No. We connected to TokenSafe without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the TokenSafe MCP server still maintained?

TokenSafe is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the TokenSafe MCP server?

VerifyMCP ran 12 checks on TokenSafe, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about TokenSafe: Authorization. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.