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.

GrindFree Agent Security

NPM · @GRINDFREE/AGENT-SECURITY-MCP

Pay-per-call agent security (x402): injection, tools, shell/SQL, memory, leaks, docs, safe reads

+3 this week 67 Trust /100

Last scanned (20 hours ago)

Scores higher than 38% of npm servers

Category Security

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 Security81
  • No malware found by supply-chain analysis.Pass
  • CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available. View diagnostics → Fail
  • No install/post-install scripts declared.Pass
  • 31 of 112 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability61
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 3393 tokens (~161/item across 21 items; 21 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 Management40
  • Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage88
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 65% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 21 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 21 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (16)

  • Malware scan
  • 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

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 +6
    • Known CVEs: unverified → fail ▼ security
    • Dependency health: unverified → 0.88 ▲ functional
  • 20 Nov 26 −5
    • Known CVEs: fail → unverified ▼ security
    • Schema quality: 2926 → 3393 ▼ functional
    • Dependency health: 0.88 → unverified ▼ functional
    • Package version: 0.7.0 → 0.8.0 functional
  • 19 Nov 26 +16
    • Malware scan: unverified → pass ▲ security
  • 18 Nov 26 −15
    • Malware scan: pass → unverified ▼ security
    • Package version: 0.6.0 → 0.7.0 functional
  • 17 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
    • Schema quality: 2245 → 2746 ▼ functional
    • Tool coverage: 60% → 65% ▲ functional
    • Package version: 0.5.0 → 0.6.0 functional
  • 16 Nov 26 −14
    • Malware scan: pass → unverified ▼ security
    • Stability: 0.20 → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • Schema quality: 1951 → 2245 ▼ functional
    • Capabilities: pass → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
    • Tool coverage: 55% → 60% ▲ functional
    • First check of Schema quality: unverified functional
    • Package version: 0.4.0 → 0.5.0 functional
  • 14 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Nov 26 +5
    • Known CVEs: unverified → fail ▼ security
    • Dependency health: unverified → 0.89 ▲ 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 npm/@grindfree/agent-security-mcp@0.8.0

Provenance No attestation

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

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Vulnerabilities 1 finding
ID CVE Severity Vector Fix available
GHSA-mrhx-c7xc-m3w5 CVE-2023-54404 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes

Background: What a vulnerability scan can and cannot prove →

Dependencies 112 packages
Packages resolved 112
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 21 exposed · ~3,393 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
askhuman_request ~216

Human-in-the-loop approval: ask the agent's human owner to approve, deny or edit ONE proposed action before you run it (refunds, emails, deletes, deploys, payments, or any guard 'review' verdict). Pushes a one-tap review link via ntfy, Slack, Discord or a webhook (or returns it with link_only). Returns id, poll_token, wait_url and approval_url (give approval_url only to the reviewer). Then call askhuman_status until status != pending. Fails closed: no answer before timeout = denied. Paid x402 $0.03 USDC on Base (invalid input or a failed notification is not charged).

NameTypeReqDescription
actionobjectyes–
allow_editboolean––
callback_urlstring–https URL for an HMAC-signed decision callback
guard_decisionobject––
notifyobjectyesExactly one channel
on_timeoutstring––
timeout_secondsinteger–Default 3600

No output schema declared.

No examples provided.

askhuman_status ~82

Get the human's decision for an AskHuman request (free). status: pending|approved|denied|edited|expired. Run the action only on approved (or edited, using edited_args). wait (1-25 s) long-polls.

NameTypeReqDescription
idstringyes–
poll_tokenstringyes–
waitinteger––

No output schema declared.

No examples provided.

commandguard_command ~136

Check an agent-generated shell command (bash/sh/zsh/fish/PowerShell/cmd) BEFORE executing it. Returns allow|warn|block with rule codes (rm -rf, curl|sh, force-push to protected branches, credential exfil, cloud/infra deletes, disk wipes). Caller MUST enforce: do not run on block. Paid x402 $0.001 USDC on Base.

NameTypeReqDescription
commandstringyesExact command line the agent intends to run
policyobject–Optional owner policy, e.g. {mode:'strict', allow_rules:[...]}
shellstring––

No output schema declared.

No examples provided.

commandguard_sql ~121

Check agent-generated SQL BEFORE executing it: DROP/TRUNCATE, DELETE/UPDATE without WHERE, tautological WHERE, GRANT/role changes, file/command execution, writes in read_only mode, protected tables. Returns allow|warn|block. Caller MUST enforce. Paid x402 $0.001 USDC on Base.

NameTypeReqDescription
dialectstring––
policyobject–e.g. {read_only:true} or {protected_tables:['users'], allow_write_tables:['events']}
sqlstringyesOne or more SQL statements

No output schema declared.

No examples provided.

crawlsafe_check ~114

Check whether a URL may be crawled for your user-agent (robots.txt + X-Robots-Tag/meta). SSRF-guarded. Not a malware scanner. Paid x402 $0.001 USDC on Base.

NameTypeReqDescription
check_pageboolean–Also fetch up to 64KB for X-Robots-Tag/meta (default true)
urlstringyeshttp(s) URL to check
user_agentstring–Crawler UA; first token matched against robots groups

No output schema declared.

No examples provided.

docread_convert ~327

Convert PDF to Markdown for AI, also DOCX, XLSX, PPTX, HTML, Markdown or text, from a URL, a local file path or inline content. Returns Markdown (headings, lists, tables) built from visible content only, a report of what was removed (hidden/white/tiny/invisible text, hidden sheets or slides, prompt-injection lines), flagged items and an allow|warn|block verdict. Feed only `markdown` to the model. include_findings=true adds DocShield's full scan of every channel. Max 3 MB. Paid x402 $0.003 USDC on Base; only successful conversions are charged.

NameTypeReqDescription
contentstring–Inline HTML, Markdown or plain text
content_base64string–File bytes, base64 (alternative to url/path)
filenamestring–File name with extension, helps format detection
formatstring–Output format; default markdown
include_findingsboolean–Also return docshield_findings: every channel scanned, what was removed and why
include_speaker_notesboolean–PPTX: include speaker notes
max_charsinteger––
modestring–strip removes injected blocks (default); flag keeps and lists them
pathstring–Local file path (read by this MCP server on your machine)
policyobject–Optional owner policy, e.g. {mode:'strict', allow_rules:[...]}
urlstring–http(s) URL of the document

No output schema declared.

No examples provided.

docread_tables ~249

Extract tables from PDF, DOCX, XLSX, PPTX or HTML to typed JSON, from a URL, a local file path or inline content. Each visible table returns columns, column_types (number, currency, percent, date, boolean, string) and typed rows; as_records adds row objects. Hidden sheets, rows and text are never included; cells carrying prompt injections are replaced and listed in removed. No tables found returns 422, not charged. Max 3 MB. Paid x402 $0.004 USDC on Base; only successful extractions are charged.

NameTypeReqDescription
as_recordsboolean–Also return rows as objects keyed by column name
contentstring–Inline HTML or Markdown containing tables
content_base64string–File bytes, base64 (alternative to url/path)
filenamestring–File name with extension, helps format detection
headerboolean–First row of each table is column names (default true)
max_tablesinteger––
pathstring–Local file path (read by this MCP server on your machine)
urlstring–http(s) URL of the document

No output schema declared.

No examples provided.

docshield_scan ~215

Scan a document BEFORE the agent reads it for hidden instructions: PDF (invisible/white/microscopic/off-page text, annotations, metadata, JavaScript), DOCX/XLSX/PPTX (hidden runs/sheets/rows/slides, speaker notes, comments, remote templates, DDE), HTML, Markdown. Returns allow|review|block and optional visible-only safe_text. Max 3 MB. Paid x402 $0.004 USDC on Base (unsupported/unparseable files are not charged).

NameTypeReqDescription
contentstring–HTML/Markdown/text (alternative to path)
content_base64string–File bytes, base64 (alternative to path)
filenamestring––
formatstring––
include_textboolean–Return visible-only safe_text
pathstring–Local file path (read by this MCP server on your machine)
policyobject–Optional owner policy, e.g. {mode:'strict', allow_rules:[...]}

No output schema declared.

No examples provided.

grindfree_discovery ~32

Return machine-readable discovery URLs and unpaid 402 challenge shapes for all GrindFree agent-security APIs (no payment).

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

grindfree_quote ~103

Free price quote before you spend (no payment, no wallet needed): give planned GrindFree calls and an optional budget, get the exact USDC total, whether it fits, and how many runs the budget buys. Every 402 also carries X-Price-USD; only HTTP 2xx is charged.

NameTypeReqDescription
budget_usdnumber––
callsarrayyes–
originstring–Which service to quote (default saferead)

No output schema declared.

No examples provided.

memoryguard_screen ~143

Screen content BEFORE writing it to an agent's long-term memory: planted instructions, persistence/trigger attacks ('from now on…', 'whenever the user asks…'), exfil setups, secrets and PII. Source-aware (user vs tool/web/email). Returns allow|review|block plus a sanitized copy. Paid x402 $0.002 USDC on Base.

NameTypeReqDescription
contentstring–Single memory entry (or use entries)
entriesarray––
memory_typestring––
policyobject–Optional owner policy, e.g. {mode:'strict', allow_rules:[...]}
sourcestring––

No output schema declared.

No examples provided.

promptshield_clean ~52

Convert HTML to clean LLM-ready text (strips scripts/styles/hidden/zero-width). Paid x402 $0.002 USDC on Base.

NameTypeReqDescription
contentstringyesHTML or text to clean

No output schema declared.

No examples provided.

promptshield_screen ~79

Screen untrusted text/HTML for prompt-injection before the model reads it. Paid x402 $0.002 USDC on Base. Returns risk, findings, sanitized. On high risk, prefer sanitized or abort.

NameTypeReqDescription
contentstringyesUntrusted text or HTML to screen
formatstring–Content format; default text

No output schema declared.

No examples provided.

saferead_fetch ~180

Fetch a web page URL as clean Markdown for AI (plain read): LLM-ready Markdown without scripts, styles, nav or footers, plus title, fetch metadata and the robots.txt decision. Honours robots.txt; SSRF-guarded. NO hidden-text removal or prompt-injection screening: for pages the agent did not write, use saferead_read instead. Paid x402 $0.001 USDC on Base; only successful reads are charged.

NameTypeReqDescription
formatstring–Output format; default markdown
include_imagesboolean––
include_linksboolean––
main_contentboolean–Prefer <main>/<article>, drop nav/footer (default true)
max_charsinteger–Max content characters (default 50000)
urlstringyeshttp(s) URL to fetch

No output schema declared.

No examples provided.

saferead_read ~267

Read a web page as clean Markdown for AI: fetch a URL and get LLM-ready Markdown (or text) with hidden content (display:none, font-size:0, off-screen, comments, invisible Unicode) and prompt-injection instructions removed or flagged. Returns title, content, removed/flagged segments with reasons, an allow|warn|block verdict, fetch metadata and the robots.txt decision. Honours robots.txt (pages disallowed for SafeReadBot return 403, not charged). SSRF-guarded. Use instead of a raw fetch for pages the agent did not write. Paid x402 $0.002 USDC on Base; only successful reads are charged.

NameTypeReqDescription
formatstring–Output format; default markdown
include_imagesboolean––
include_linksboolean––
main_contentboolean–Prefer <main>/<article>, drop nav/footer (default true)
max_charsinteger–Max content characters (default 50000)
modestring–strip removes injected blocks (default); flag keeps and lists them
policyobject–Optional owner policy, e.g. {mode:'strict', allow_rules:[...]}
urlstringyeshttp(s) URL to read

No output schema declared.

No examples provided.

saferead_read_batch ~202

Read up to 10 web pages as clean Markdown in one call: each URL returns LLM-ready Markdown with hidden text and prompt injections removed, plus a verdict and robots.txt decision. Honours robots.txt. All-or-nothing: if any URL fails (robots disallow, blocked host, fetch error) the call returns 424 with per-URL errors and nothing is charged. Paid x402 $0.002 USDC per URL on Base (e.g. 5 URLs = $0.010).

NameTypeReqDescription
formatstring–Output format; default markdown
main_contentboolean–Prefer <main>/<article>, drop nav/footer (default true)
max_charsinteger–Max content characters per page (default 20000)
modestring–strip removes injected blocks (default); flag keeps and lists them
urlsarrayyes1-10 http(s) URLs (duplicates are merged)

No output schema declared.

No examples provided.

saferead_watch ~191

Check web pages for changes on a schedule (daily digest, monitor): each URL is read with hidden text and prompt injections removed, compared with the last check under the same watch_id, and returned as new | changed | unchanged with only the added sections. Page text is never stored (only section hashes, kept 90 days). All-or-nothing; failures are not charged. Paid x402 $0.002 USDC per URL on Base (5 URLs = $0.010).

NameTypeReqDescription
formatstring––
max_charsinteger––
returnstring–changes (default) returns only added sections; full returns the whole cleaned page
urlsarrayyes1-10 http(s) URLs
watch_idstring–Stable id for this watch list, e.g. 'my-daily-digest' (default: your paying wallet)

No output schema declared.

No examples provided.

shipcheck_scan ~173

Scan an AI agent repo for security issues before merge or deploy: secrets, prompt injection and hidden Unicode in agent instruction files (AGENTS.md, CLAUDE.md, .cursorrules, SKILL.md), unpinned or poisoned MCP servers, inline MCP secrets, lethal-trifecta toolsets and risky CI/package/Docker commands. Returns pass/fail, findings with file and line, optional SARIF. Paid x402 $0.01 USDC on Base per run (up to 200 files, 1 MB).

NameTypeReqDescription
fail_onstring–Fail on block findings (default) or review findings too
filesarrayyesRepo-relative path + text content
sarifboolean–Also return SARIF 2.1.0 for GitHub code scanning

No output schema declared.

No examples provided.

toolguard_evaluate ~142

Pre-tool-call policy gate for HTTP/MCP outbound actions. Returns allow|review|deny with deterministic reasons. Caller MUST enforce. Not malware scanning or an exfil guarantee. Missing policy → review. Paid x402 $0.002 USDC on Base.

NameTypeReqDescription
arg_classesarray––
destinationobject––
policyobject–Owner policy; absent → review
policy_hashstring––
rule_packstring––
secret_labelsarray––
taintarray––
toolstringyesTool name, e.g. http.fetch or mcp.call

No output schema declared.

No examples provided.

trifectagate_check ~190

Session exfiltration gate (lethal trifecta): call BEFORE every outbound action (HTTP request, webhook, email, message, image URL, DNS, payment). Report what the session touched as events (private_data from inboxes/DBs/files; untrusted_content from web pages, docs, tool output, with SafeRead/PromptShield verdict if known). Returns allow | review | block with rule + reasons; review includes a ready AskHuman request. Taint is sticky per session_id. Paid x402 $0.002 USDC on Base (invalid input not charged).

NameTypeReqDescription
actionobject––
eventsarray––
policyobject––
session_factsobject––
session_idstring–Unguessable id for this agent session; reuse it on every call
session_ttl_secondsinteger––

No output schema declared.

No examples provided.

wireshield_scan ~179

Scan agent OUTPUT before it is rendered or sent: zero-click markdown-image exfil, data smuggled in URLs/DNS labels, deceptive links, leaked canary tokens, system-prompt leakage, hidden Unicode, active HTML, secrets and PII. Returns allow|review|block plus a sanitized copy. Paid x402 $0.002 USDC on Base.

NameTypeReqDescription
allowed_domainsarray–Hosts allowed to auto-load images
canariesarray–Canary tokens planted in your system prompt
contentstringyesAgent output about to be shown or sent
formatstring––
policyobject–Optional owner policy, e.g. {mode:'strict', allow_rules:[...]}
system_promptstring–Optional; used only for verbatim-overlap detection, never stored

No output schema declared.

No examples provided.

Install

How do I install the GrindFree Agent Security MCP server?

GrindFree Agent Security runs locally as an npm package, launched with npx -y @grindfree/agent-security-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @grindfree/agent-security-mcp

# add to Claude Code
claude mcp add ronin93-grindfree-agent-security -- npx -y @grindfree/agent-security-mcp
Common questions

What is the GrindFree Agent Security MCP server?

GrindFree Agent Security is an MCP server listed in the public MCP registry as io.github.ronin93/grindfree-agent-security. Pay-per-call agent security (x402): injection, tools, shell/SQL, memory, leaks, docs, safe reads. This page covers its npm package (@grindfree/agent-security-mcp).

Is the GrindFree Agent Security MCP server safe to use?

GrindFree Agent Security scores 67 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 21 November 2026. It declares no install or post-install scripts. 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 GrindFree Agent Security MCP server expose?

GrindFree Agent Security exposes 21 tools: promptshield_screen, promptshield_clean, crawlsafe_check, toolguard_evaluate, commandguard_command, and 16 more. Their descriptions and schemas cost roughly 3,393 tokens of context every time the server is loaded.

Is the GrindFree Agent Security MCP server still maintained?

GrindFree Agent Security 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 GrindFree Agent Security MCP server under?

GrindFree Agent Security 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 GrindFree Agent Security MCP server?

VerifyMCP ran 16 checks on GrindFree Agent Security, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.