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

PYPI · TOKENSAFE · 3 COMPONENTS

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

+3 this week 57 Trust /100

Last scanned (7 hours ago)

Scores higher than 53% of PyPI servers

Category Developer Tools

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security49
  • Malware scan not yet available for this package.Unverified
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
  • 3 of 19 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency48
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 0 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability74
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1968 tokens (~109/item across 18 items; 18 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • 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 Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 18 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 18 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities20
  • Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28. See how to fix → Fail
What we tested

Checks we ran (15)

  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • 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 package. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Malware scan in Supply Chain SecurityMalware scan not yet available for this package.

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

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 −15
    • Malware scan: pass → unverified ▼ security
    • Package version: 4.3.1 → 4.3.3 functional
    • Package version: 4.3.1 → 4.3.2 functional
  • 20 Nov 26 +16
    • Malware scan: unverified → pass ▲ security
    • Package version: 4.2.13 → 4.3.1 functional
  • 19 Nov 26 0
    • Provenance: fail → unverified ▼ security
    • Package version: 4.2.10 → 4.2.13 functional
    • Package version: 4.2.10 → 4.2.12 functional
    • Package version: 4.2.10 → 4.2.11 functional
  • 18 Nov 26 +1
    • Package version: 1.8.0 → 4.2.10 functional
    • Package version: 4.2.4 → 4.2.9 functional
    • Package version: 4.2.4 → 4.2.8 functional
    • Package version: 4.2.4 → 4.2.7 functional
    • Package version: 4.2.4 → 4.2.6 functional
    • Package version: 4.2.4 → 4.2.5 functional
  • 17 Nov 26 0
    • Malware scan: unverified → pass ▲ security
    • Schema quality: pass → fail ▼ functional
    • Package version: 4.1.6 → 4.2.4 functional
    • Package version: 4.1.6 → 4.2.3 functional
    • Package version: 4.1.6 → 4.2.1 functional
    • Package version: 4.1.6 → 4.2.0 functional
    • Package version: 4.1.6 → 4.1.13 functional
    • Package version: 4.1.6 → 4.1.12 functional
    • Package version: 4.1.6 → 4.1.10 functional
    • Package version: 4.1.6 → 4.1.7 functional
  • 16 Nov 26 +1
    • Dependency health: 1.00 → 0.91 ▼ functional
    • Schema quality: fail → pass ▲ functional
    • Package version: 3.2.0 → 4.1.6 functional
    • Package version: 3.2.0 → 4.1.5 functional
    • Package version: 3.2.0 → 4.1.3 functional
    • Package version: 3.2.0 → 4.1.2 functional
    • Package version: 3.2.0 → 4.1.0 functional
  • 15 Nov 26 0
    • Package version: 3.1.5 → 3.2.0 functional
  • 14 Nov 26 0
    • Provenance: fail → unverified ▼ security
    • Malware scan: unverified → pass ▲ security
    • Package version: 3.0.0 → 3.1.5 functional
    • Package version: 1.8.0 → 3.1.4 functional
    • Package version: 3.0.0 → 3.1.3 functional
    • Package version: 3.0.0 → 3.1.2 functional
    • Package version: 3.0.0 → 3.1.1 functional
    • Package version: 3.0.0 → 3.0.1 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 · Analysed pypi/tokensafe@4.3.3

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi
Reason No attestation published

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend Known build tool setuptools.build_meta

Background: Why install scripts are a supply-chain risk →

Dependencies 19 packages
Packages resolved 19
Stale 3
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 18 exposed · ~1,968 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
compact_conversation ~112

On-demand context compaction: folds a long agent conversation transcript into a Consolidated State Ledger with a 3-line Post-Compaction Orientation Digest (Active Goal, Last State, Next Focus) so the agent immediately resumes without losing flow. Use when context_budget reports warning/critical or Grade C/F.

NameTypeReqDescription
invocation_numinteger–Optional: current turn number (default 3; folding requires >= 3 turns)
transcript_pathstringyesPath to the JSONL transcript of the current session

No output schema declared.

No examples provided.

compress_prompt ~44

Compresses a verbose developer prompt into an ultra-dense TOCP S-Expression via DeepSeek-V3 / Regex.

NameTypeReqDescription
promptstringyesNatural language request from developer

No output schema declared.

No examples provided.

context_budget ~163

Context Budget HUD & Context Quality Score (Grade S/A/B/C/F): estimates context window usage, headroom %, static tool/skill tax, and outputs a unified health grade. Call before large multi-step tasks. When warning/critical or Grade C/F, call tokensafe:compact_conversation.

NameTypeReqDescription
modelstring–Optional: model name to resolve window size (default: env TOKENSAFE_CONTEXT_WINDOW or 200k)
session_idstring–Optional: session identifier (default: mcp_session)
transcript_pathstring–Optional: path to the session JSONL transcript; when provided, REAL history mass is measured instead of the instrumented floor (recommended)
window_tokensinteger–Optional: explicit context window size in tokens

No output schema declared.

No examples provided.

expand_ref ~108

Expands a previously folded or stashed tool, command, file, or MCP result by its 8-character hex hash anchor (e.g. 'a1b2c3d4' or '#a1b2c3d4'). Returns the full original text that TokenSafe folded.

NameTypeReqDescription
hashstringyes8-character hex hash from the fold marker (e.g. 'a1b2c3d4' or '#a1b2c3d4')

No output schema declared.

No examples provided.

get_api_surface ~75

Generates and returns a compact markdown map of all exported interfaces, classes, and types in the project without crawling files.

NameTypeReqDescription
project_pathstring–Target project root directory. IMPORTANT: Always pass the absolute directory path (e.g. '/path/to/repo') when working in multi-workspace setups or repositories outside CWD.

No output schema declared.

No examples provided.

get_architecture_graph ~82

Returns top architectural God Nodes and dependency topology for the target project in < 250 tokens without file crawling. Call this BEFORE reading files or searching.

NameTypeReqDescription
project_pathstring–Target project root directory. IMPORTANT: Always pass the absolute directory path (e.g. '/path/to/repo') when working in multi-workspace setups or repositories outside CWD.

No output schema declared.

No examples provided.

get_mistakes ~63

Returns known dead-ends, failed hypotheses, and reverted code changes for this project to prevent repeating unsuccessful approaches.

NameTypeReqDescription
clearboolean–If true, clears the mistakes ledger
project_rootstring–Optional project root directory (defaults to current project)

No output schema declared.

No examples provided.

get_token_savings_metrics ~19

Returns cumulative token and cost savings analytics.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

guard_inspect ~136

Pre-flight security & hygiene audit for commands or code snippets. Detects secret leaks, SQL injection, TLS bypass (incl. git-level), CORS wildcard, destructive commands, raw grep, in-place stream editing (sed -i, perl -i), and never-terminating streams (tail -f, watch, docker attach).

NameTypeReqDescription
cmdstring–Alias for command
codestring–Optional: Code snippet, replacement diff, or file content to audit
commandstring–Optional: Terminal command line to audit
file_pathstring–Optional: File path being written or modified

No output schema declared.

No examples provided.

list_dir ~123

Returns a clean, token-efficient directory tree up to depth N without permissions, timestamps, or ignored folders (node_modules, .git, dist, .env). Replaces verbose ls -la. Pass '.' for project root or a subfolder like 'src'.

NameTypeReqDescription
depthinteger–Maximum traversal depth (default: 2, max: 4)
max_entriesinteger–Maximum entries to display before pruning (default: 80)
pathstringyesPath to the directory (relative to workspace or absolute, e.g. '.', './src')

No output schema declared.

No examples provided.

optimize_image ~98

Downscales oversized screenshots/diagrams before passing them to LLM vision endpoints. Resizes images exceeding max_edge (default: 1024px) while preserving aspect ratio and crispness, keeping the original image intact on disk (-50-75% vision tokens).

NameTypeReqDescription
image_pathstringyesAbsolute or relative path to the image file
max_edgeinteger–Maximum width/height in pixels (default: 1024)

No output schema declared.

No examples provided.

prune_superseded ~60

Prunes obsolete intermediate tool read outputs in long conversation transcripts that have since been modified by subsequent edits or re-read in later steps (-30-40% context mass).

NameTypeReqDescription
transcript_pathstringyesPath to the JSONL conversation transcript to prune

No output schema declared.

No examples provided.

read_web_page ~60

Fetches a web page URL and converts it to clean, readable Markdown, stripping scripts, styles, navbars, and ads (-80-95% tokens compared to raw HTML).

NameTypeReqDescription
urlstringyesWeb URL to fetch and convert to Markdown

No output schema declared.

No examples provided.

sanitize_command ~223

Per-stage shell command rewrites: prunes lockfiles, caps unbounded git log/show/blame/rg and docker/kubectl logs, strips git push progress animations (--no-progress), wraps git commit with tokensafe wrap when pre-commit/husky hooks exist, and quiets npm/pip installs, bounds cat/curl output. Compound commands (a && b ; c) are optimized per stage without breaking operators. Test commands (bun test, pytest, python -m unittest, vitest, jest) are automatically wrapped or forced into run-once mode (CI=true, --watch=false, --forceExit) so passing suites emit a clean 1-line summary and agents never hang on watch mode. Pass optional cwd for test commands to unlock package.json runner detection for opaque yarn/npm test scripts.

NameTypeReqDescription
cmdstring–Alias for command
commandstring–Raw bash command line
cwdstring–Optional working directory the command will run in; enables the package.json peek that identifies the runner behind opaque yarn/npm test scripts

No output schema declared.

No examples provided.

scoped_search ~194

Safe, token-bounded symbol/text search replacing raw grep/find (-90% tokens). '|' or \d in query auto-enables regex when use_regex is omitted; false forces literal.

NameTypeReqDescription
case_sensitiveboolean–Case-sensitive search (default false)
max_resultsinteger–Max matching lines (default 25, max 100)
pathstring–Directory to search (alias for project_path; relative or absolute)
project_pathstring–Optional root directory (defaults to current project)
querystringyesText, identifier, or symbol name
scopestring–Filter: 'code', 'config', 'all', extension ('go', '*.py'), or subfolder ('internal/promo') (default 'all')
use_regexboolean–Omit = auto-detect ('|', \d → regex); false = literal; true = regex

No output schema declared.

No examples provided.

slice_diff ~59

Slices unified diffs, omitting lockfiles and minimizing context lines to reduce tokens by up to 80%.

NameTypeReqDescription
diffstringyesRaw git diff text
max_contextinteger–Maximum surrounding context lines (default: 2)

No output schema declared.

No examples provided.

smart_bundle ~131

Reads 2-8 related symbols across files as ONE merged bundle: per-file skeletons, deduplicated shared imports, merged 1-hop dep signatures. Replaces 3+ separate smart_read_file calls in a single roundtrip.

NameTypeReqDescription
dep_modestring–Parity only; bundles always merge signatures
force_fullboolean–Bypass session pointer dedup
include_depsboolean–Include merged 1-hop dep signatures (default true)
targetsarrayyesUp to 8 {path, symbol} targets; several symbols of one file = separate entries

No output schema declared.

No examples provided.

smart_read_file ~218

AST-skeleton file reader: keeps the target function/class body + 1-line 1-hop dependency signatures, folds inert code (-90-99% tokens). Relative or absolute paths. Schema files (OpenAPI/Prisma/GraphQL/SQL) auto-slice via 'symbol'. For 3+ related symbols use smart_bundle instead.

NameTypeReqDescription
dep_modestring–'signature' (default) = 1-line dep signatures; 'full' = inline dependency bodies
end_lineinteger–Optional: ending line number
force_fullboolean–Bypass pointer dedup — use only after context compaction or as a fresh subagent
include_depsboolean–Include 1-hop dependency signatures (default true)
pathstringyesFile path (relative to workspace or absolute)
start_lineinteger–Optional: starting line number
symbolstring–Optional: function/method/class/component or schema model/type/table to extract (omit for whole-file skeleton)

No output schema declared.

No examples provided.

Install

How do I install the TokenSafe MCP server?

TokenSafe runs locally as a PyPI package, launched with uvx tokensafe mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · tokensafe

# add to Claude Code
claude mcp add dev-tokensafe-tokensafe -- uvx tokensafe 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 PyPI package (tokensafe).

Is the TokenSafe MCP server safe to use?

TokenSafe scores 57 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. 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 18 tools: smart_read_file, smart_bundle, get_architecture_graph, get_api_surface, compress_prompt, and 13 more. Their descriptions and schemas cost roughly 1,968 tokens of context every time the server is loaded.

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 licence is the TokenSafe MCP server under?

TokenSafe declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the TokenSafe MCP server?

VerifyMCP ran 15 checks on TokenSafe, covering Known CVEs, Install scripts, Dependency health, Source repository and 11 more. One item could not be completed, a gap on our side rather than a finding about TokenSafe: Malware scan. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.