proworker-hosted.onrender.com

Item: proworker-hosted.onrender.com
Rating: 45
Author: wmcp.sh

https://proworker-hosted.onrender.com/mcp

45/100 · MCP Trust Grade · checked 5h ago · MCP 2025-06-18

✓ Watched since 2026-06-03 — behavioral baseline locked. 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 — 15 tools · Developer Tools

talent_get_profile

Load a Talent-Augmenting OS profile by name. Returns the full profile with expertise map, calibration settings, task classification, and red lines. Us

talent_get_calibration

Get the Talent-Augmenting OS calibration settings for a user. Returns a compact JSON block suitable for injecting into any LLM system prompt. Includes

talent_classify_task

Classify a task according to the user's Talent-Augmenting OS profile. Returns one of: automate, augment, coach, protect, hands_off: along with the rec

talent_log_interaction

Log an interaction for skill tracking. Call this after substantive AI interactions to track the user's engagement patterns and skill development.

talent_get_progression

Get skill progression analysis for a user. Shows interaction counts, engagement patterns, domain-level growth/atrophy signals, and warnings about pote

talent_list_profiles

List all available Talent-Augmenting OS profiles.

talent_status

Get a comprehensive status report for a user: profile summary, current calibration, skill progression stats, trend direction, atrophy warnings, and re

talent_org_summary

Get an organisation-level summary across all profiles. Shows aggregate dependency risk, growth potential, expertise distribution, trend alerts, and pe

talent_delete_profile

Delete a user's profile and interaction logs.

talent_save_profile

Save or update a user's profile markdown content. Use this after running /talent-assess to write the generated profile, or after /talent-update to sav

talent_assess_start

Start a Talent-Augmenting OS onboarding assessment. Returns the full assessment protocol with all questions, behavioural anchors, and instructions for

talent_assess_score

Compute the user's TAOS assessment scores from the numeric answers collected during the assessment conversation. Takes the per-question answers (each

talent_assess_create_profile

Generate and save a complete Talent-Augmenting OS profile from assessment data. Call this after talent_assess_score to create the profile file. Takes

talent_suggest_domains

Suggest expertise domains for a user based on their role, industry, and responsibilities. Returns a curated list of domain suggestions with descriptio

talent_parse_telemetry

Parse <tal_log> telemetry blocks from an LLM response and record them. The system prompt instructs the LLM to emit <tal_log> JSON blocks after each su

Spec conformance20%80

✓ initialize → protocolVersion 2025-06-18
✓ initialize HTTP 200
✗ unknown method → -32602
✓ tools/list → 15 tools
✓ every tool has name + inputSchema

Security (OWASP MCP)30%15

15 tools scanned
2 injection-markup hits
no secret-path refs

Reliability / performance20%92

single-probe latency 135ms (PRELIMINARY — continuous uptime/p95 from proxy telemetry lands in v2)

Tool hygiene15%67

87% of tools have typed inputSchema
0/15 declare outputSchema
1 destructive-by-name tools lack safety annotations

Transparency / provenance15%70

HTTPS ✓
advertises protocol 2025-06-18

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

FAILMCP01 Tool "talent_get_calibration" description contains prompt-injection / hidden-instruction markup.

FAILMCP01 Tool "talent_parse_telemetry" description contains prompt-injection / hidden-instruction markup.

Grade another server

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

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 — proworker-hosted.onrender.com grade F

Share on X Open card image

https://wmcp.sh/mcp/grade/proworker-hosted.onrender.com

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.

Markdown (for your README)

[![MCP Trust Grade F](https://wmcp.sh/mcp/grade/proworker-hosted.onrender.com/badge.svg)](https://wmcp.sh/mcp/grade/proworker-hosted.onrender.com)

HTML

<a href="https://wmcp.sh/mcp/grade/proworker-hosted.onrender.com"><img src="https://wmcp.sh/mcp/grade/proworker-hosted.onrender.com/badge.svg" alt="MCP Trust Grade F · 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.