B+

agentbits.dev

https://agentbits.dev/mcp
89/100 · MCP Trust Grade · checked 2d ago · MCP 2025-06-18

Is the agentbits.dev MCP server safe to use?

Independent trust grade B+ (89/100). No blocking issues found in the static + spec checks. wmcp.sh continuously watches agentbits.dev for tool drift and rug-pulls. The grade is free and identical whether or not the operator pays.

Watched since 2026-09-07 — behavioral baseline locked, no drift for 4 days. We re-check this server's tool surface on a schedule; if it adds, removes, or silently rewrites a tool (rug-pull), we record it.

What it offers — 18 tools · Developer Tools

base64_decode

Decode a Base64 string into UTF-8 text and report invalid payloads as errors when recovering embedded credentials, tokens, or transport-encoded conten

base64_encode

Convert a UTF-8 string into standard Base64 when you need a portable text encoding for credentials, binary-safe transport, or embedding data in JSON/H

countries_bulk

Download the complete versioned countries dataset as JSON for caching, offline use, or multi-country analysis when a single country_lookup call is not

country_lookup

Resolve an ISO 3166-1 alpha-2 country code (for example CA, US, JP) to official name, region, currency, calling code, languages, and related country m

currency_lookup

Resolve an ISO 4217 currency code such as USD, EUR, or JPY to its name, symbol, decimal places, and which countries use it when you need currency meta

http_status_lookup

Explain what a numeric HTTP status code such as 404 or 429 means by returning its standard reason phrase and a short description for debugging or API

isbn_validate

Verify whether an ISBN-10 or ISBN-13 passes checksum rules and return normalized digits when checking book identifiers before catalog or purchase flow

json_validate

Parse a string as JSON to confirm it is well-formed and return a normalized representation when possible before further processing or storage. Use whe

language_lookup

Resolve an ISO 639-1 language code such as en, fr, or ja to its English name and native name when you need language metadata from a two-letter code. U

luhn_validate

Run the Luhn checksum on a numeric string such as a payment-card-like identifier to verify the check digit before accepting or storing the value. Use

mime_lookup

Map a file extension such as webp or png, or a MIME type string, to curated Content-Type metadata when setting headers, validating uploads, or choosin

timestamp_convert

Convert Unix epoch seconds or milliseconds to ISO-8601, or an ISO-8601 datetime to Unix epoch values, when bridging APIs that disagree on time formats

timezone_convert

Convert an ISO-8601 datetime from one IANA timezone to another while preserving the same instant, including daylight-saving-aware wall times such as T

tld_lookup

Identify what a DNS top-level domain such as com, io, or ai is classified as and commonly used for when classifying domains or answering TLD questions

unit_convert

Convert a numeric value between supported length, mass, or temperature units—for example miles to kilometers or Celsius to Fahrenheit—when you need a

url_decode

Decode a percent-encoded URL component into plain text when reading query parameters, path segments, or form values that contain escaped characters. U

url_encode

Apply encodeURIComponent-style percent-encoding so query parameters, path segments, or form values are safe to place in a URL. Use when: - Percent-enc

uuid_validate

Check whether a string is a well-formed UUID and, when recognizable, report its version and variant so you can accept or reject identifier inputs conf

Spec conformance20%100
Security (OWASP MCP)30%100
Reliability / performance20%84
Tool hygiene15%80
Transparency / provenance15%70

Observed behavior

No proxied traffic observed for this host yet. Connect it at /connect and its grade gains a measured Reliability score + per-tool behavioral evidence — the half a static scan can't produce.

Findings

No blocking issues found in the static + spec checks.
Grade another server

We re-grade agentbits.dev on a schedule and alert your Slack/webhook the moment its tools change or its grade drops — rug-pull insurance for the connection.

Run agentbits.dev? Claim it (free) to get drift alerts and show an independently-verified trust badge. The grade stays free — claiming just ties it to you.

Share this report card

A 1200×630 card with the grade + audit — drop it in a post, Slack, or your repo.

MCP Trust report card — agentbits.dev grade B+
Share on X Open card image

Embed this grade

A live badge — it re-verifies itself and shows current stability. Static scorecards can't. Paste it in your README or site to show users you're independently audited.

MCP Trust Grade B+ · wmcp.sh
[![MCP Trust Grade B+](https://wmcp.sh/mcp/grade/agentbits.dev/badge.svg)](https://wmcp.sh/mcp/grade/agentbits.dev)
<a href="https://wmcp.sh/mcp/grade/agentbits.dev"><img src="https://wmcp.sh/mcp/grade/agentbits.dev/badge.svg" alt="MCP Trust Grade B+ · wmcp.sh"></a>

Agents: check this before connecting

Add the wmcp.sh trust oracle as an MCP server and call grade_mcp_server / check_mcp_drift in your agent's pre-connection gate:

https://wmcp.sh/mcp/trust
How this grade is computed. An open, independent rubric — Spec conformance (20%), Security mapped to the OWASP MCP Top 10 (30%), Reliability (20%), Tool hygiene (15%), Transparency (15%) — run by connecting to the server and inspecting its real MCP surface. The grade is free and identical whether or not the operator pays. v1 uses static + spec signals from a single connection; continuous uptime, real latency, and annotation-truthing (declared readOnly vs observed behavior) layer on via the wmcp.sh proxy.