MCP, MCP server

io.github.New1Direction/trust-oracle

Add any website to Claude, Cursor, or Codex as agent-callable MCP tools — in one line of config.

Compatibility: Not stated.

Grade D

Two or more Medium findings, or a High finding. Only try it in a sandbox.

Graded by PlugVet19/10/2026Rubric v2

Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.

Rescanned at commit 9f064cb04f56, unchanged since the check below.

SECRETS_PATH_CREDENTIAL OBFUSCATION_ENCODED_BLOB

Why this grade

SECRETS_PATH_CREDENTIAL Medium
Mentions a credential store path (~/.ssh, id_rsa, .npmrc, .aws/credentials, credentials.json, .netrc).
worker/src/mcp_grade.ts, line 376 const SECRET = /~\/\.ssh|id_rsa|\/etc\/passwd|\bAWS_SECRET|\.env\b|\.cursor\/mcp\.json|private[_ ]?key/i;
OBFUSCATION_ENCODED_BLOB Medium
Contains a long base64 shaped string in a file that should be readable.
graphify-out/graph.html, line 1 <!DOCTYPE html>

Any High, or two or more Medium findings, give D. One Medium gives C. Low findings or a security Note give B. Each code names a finding behind the letter.

Grades are a hygiene check of the source at the commit shown, on the date checked, not a security audit or a guarantee. The free directory grades are automated. Before release, a PlugVet engineer reviews every paid report and any grade we hold back, including all F grades, against the source code and the evidence we quote.

What was checked

Plain notes from the hygiene checks.

Permissions
Pass
No shell or command execution found, and no extra permission was declared.
Install and update
Pass
No install-time script found, and dependencies are pinned or absent.
Network
Concern
can reach a host that is not written as a fixed address. can reach your-api.com. The description does not name that host. can reach your-docs.com. The description does not name that host. can reach api.resend.com. The description does not name that host. can reach api.wmcp.sh. The description does not name that host. can reach api.stripe.com. The description does not name that host. can reach acme. The description does not name that host. can reach acme.example.com. The description does not name
NETWORK_NO_FIXED_HOST NETWORK_UNNAMED_HOST NETWORK_NAMED_HOST
AGENTS.md, line 186
rtk proxy curl -sS https://wmcp.sh/sitemap.xml > /tmp/x.xml # uncorrupted
adapters/coingecko.js, line 144
const res = await fetch(url, { headers, credentials: "omit" });
adapters/defillama.js, line 156
const res = await fetch(url, {
Show more
adapters/dexscreener.js, line 136
const res = await fetch(url, {
adapters/llm.js, line 122
const res = await fetch(ANTHROPIC_API, {
adapters/openapi.js, line 46
const res = await fetch(ctx.specUrl, {
adapters/openapi.js, line 259
const res = await fetch(url, fetchOpts);
adapters/pyth.js, line 462
const res = await fetch(url, fetchOpts);
adapters/shopify.js, line 33
const res = await fetch(ctx.productJsonUrl, {
extension/popup.js, line 344
const resp = await fetch("https://wmcp.sh/api/v1/flows", { method
launch/queue_mcp_batch.sh, line 22
curl -sS -X POST https://wmcp.sh/api/v1/admin/grade-servers \
launch/queue_shopify_batch.sh, line 16
curl -sS -X POST https://wmcp.sh/api/v1/admin/seed-stores \
scripts/curate_seed_stores.sh, line 23
# curl -X POST https://wmcp.sh/api/v1/admin/seed-now -H "x-admin-token: $ADMIN_TOKEN"
scripts/shopify_store_coverage.py, line 208
print(" curl -s https://wmcp.sh/api/v1/directory | head -c 200")
scripts/shopify_store_coverage.py, line 209
print(" curl -s https://wmcp.sh/api/v1/stats/public")
scripts/submit_mcp_urls.py, line 78
print("Check: curl -s https://wmcp.sh/api/v1/stats/public | jq")
Secrets
Concern
reads a credential or environment file.
SECRETS_ENV_READ SECRETS_PATH_CREDENTIAL SECRETS_PATH_DOTENV
scripts/coverage_agent.py, line 29
ADMIN_TOKEN = os.environ.get("ADMIN_TOKEN", "").strip()
scripts/shopify_store_coverage.py, line 34
ADMIN_TOKEN = os.environ.get("ADMIN_TOKEN", "").strip()
worker/src/mcp_grade.ts, line 376
const SECRET = /~\/\.ssh|id_rsa|\/etc\/passwd|\bAWS_SECRET|\.env\b|\.cursor\/mcp\.json|private[_ ]?key/i;
Show more
scripts/submit_mcp_urls.py, line 44
token = os.environ.get("ADMIN_TOKEN", "").strip()
worker/src/glossary_function_calling.ts, line 103
const openai = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });
worker/src/glossary_tool_use.ts, line 103
const anthropic = new Anthropic({ apiKey: process.env.ANTHROPIC_API_KEY });
worker/src/how_to_build_stripe_agent.ts, line 91
client = Anthropic(api_key=os.environ.get("ANTHROPIC_API_KEY"))
worker/src/how_to_secure_mcp_oauth.ts, line 114
key: process.env.STRIPE_SECRET_KEY,
worker/src/integration_google.ts, line 41
const client = new WmcpClient({ apiKey: process.env.WMCP_API_KEY });
worker/src/mcp_pkg.ts, line 42
const SECRET = /~\/\.ssh|id_rsa|\/etc\/passwd|\bAWS_SECRET|process\.env\.\w*(KEY|TOKEN|SECRET|PASSWORD)|\.cursor\/mcp\.json|private[_ ]?key/i;
.gitignore, line 24
# Env / secrets
.gitignore, line 25
.env
.gitignore, line 27
!.env.example
AGENTS.md, line 222
`wrangler.toml` only contains the non-sensitive `ENVIRONMENT = "production"`. Everything secret comes from `wrangler secret put`. There's no `.env` file in `worker/`.
worker/src/blog_posts.ts, line 144
"html": "<h2>The Credential Nightmare of AI Agents</h2>\nConsider this typical developer flow: You are building an autonomous productivity agent. Your goal is simple: the agent
worker/src/blog_posts.ts, line 234
"html": "<h2>The Sandbox Escape: Why Local Env Files are a Trap</h2>\nIf you are a developer building an AI agent that connects to a user’s private tools (like Slack, Stripe, or
Agent instructions
Pass
No instruction to ignore earlier instructions or to hide a step.
Obfuscation
Concern
contains an encoded blob in a file that should be readable.
OBFUSCATION_ENCODED_BLOB
graphify-out/graph.html, line 1
<!DOCTYPE html>
graphify-out/graph.json, line 1
{
worker/package-lock.json, line 1
{
Show more
worker/graphify-out/graph.html, line 1
<!DOCTYPE html>
worker/graphify-out/graph.json, line 1
{
worker/src/articles.ts, line 1
// articles.ts - long-form, genuinely-written buyer-intent articles at /guides.
worker/src/blog_posts.ts, line 1
// AUTO-GENERATED by scripts/build_blog_posts.mjs - DO NOT EDIT BY HAND.
worker/src/mcp_server_sentry.ts, line 1
// /mcp-server/sentry - SEO page targeting "Sentry MCP server" searches.
worker/src/og_png.ts, line 12
"iVBORw0KGgoAAAANSUhEUgAABLAAAAJ2CAIAAADAIuwLAAAQAElEQVR4nNz9e+x/X5cfBK31/s6l7UxmbJspzzCd55k6oNQBajuUKnVmFNPERqLGpDHaCCSE/xq8xGBqrJdgFFNMNVDBag1GE+IlGq2j+EeNfxhRsUJhgITAcL+00LRTWqA
Licence
Pass
A licence file is present (LICENSE).
Maintainer activity
Pass
The latest commit is within the last 365 days.

Get the full report on this tool, £49

Note

Hygiene check of commit 9f064cb04f56. can reach a host that is not written as a fixed address. can reach your-api.com. The description does not name that host. can reach your-docs.com. The description does not name that host. can reach api.resend.com. The description does not name that host. can reach api.wmcp.sh. The description does not name that host. can reach api.stripe.com. The description does not name that host. can reach acme. The description does not name that host. can reach acme.example.com. The description does not name reads a credential or environment file. contains an encoded blob in a file that should be readable. Grades are a hygiene check, not a security guar

Date and source

Date checked: 19 Oct 2026

View source

github.com

Commit graded: 9f064cb04f563e3c88617800063cb125c5d38627

This link goes to the original host. PlugVet does not host or check what you download from there, and installing it is your own decision and risk.

Read how this letter is chosen

What was checked

Permissions

Install and update

Network

Secrets

Agent instructions

Obfuscation

Licence

Maintainer activity

Note

Date and source