MCP.Market

Course Drift Oracle MCP server

online · 100% uptime
by 710git·io.github.710git/course-drift-oracle·v1.0.0
No reviews yet

Signed drift reports for the ai-agents-for-beginners course. Free summary; $0.25 full report.

B80/100grade B
Write a reviewRun it
What users say
No reviews yet
Be the first
Safety scan
B80/100

full report

Adoption
New

0 stars

Reviews

Write one

Nobody has reviewed Course Drift Oracle yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Course Drift Oracle tools (10)

write = sends, deletes, buys or posts
  • drift_reportFree

    Paid ($0.25). Every drift finding with file path, line number, what is wrong, and the suggested fix - enough to open a PR without re-deriving anything. Verifiable against the free summary's findings_hash.

  • drift_report_x402Free

    Paid ($0.25, x402/USDC). Same full drift report as drift_report: every finding with file path, line number, what is wrong, and the suggested fix. Pay with x402 if you hold USDC; use drift_report to pay by card or other MPP methods.

  • drift_summaryFree

    Free. How many pinned models and package versions in the ai-agents-for-beginners course have drifted from upstream reality, broken down by lesson and severity. Returns a signed receipt committing to the full findings set. No payment required.

  • model_statusFree

    Free. Look up one model id in the signed catalog: current, deprecated, or retired, plus replacement, earliest_retirement, source, and retrieved. Returns an honest "unknown: not in catalog" for an id this catalog does not track - never conflated with "current". Includes the catalog snapshot's signed receipt.

  • model_status_batchFree

    Paid ($0.10). Look up a list of model ids in the signed catalog and return one entry per id (or an honest "unknown: not in catalog" per id), plus any_action_needed: true if any input model is deprecated or retired. Built for a CI pipeline's pinned-model set - one signed answer and one boolean to gate a build on, instead of parsing an array of free lookups by hand.

  • model_status_batch_x402Free

    Paid ($0.10, x402/USDC). Same batch model status lookup as model_status_batch: one entry per input id plus any_action_needed. Pay with x402 if you hold USDC; use model_status_batch to pay by card or other MPP methods.

  • site_auditFree

    Paid ($0.25). All 12 agent-legibility checks for a submitted site URL, each with status and detail, as a dated receipt signed live with a dedicated Ed25519 audit key (or explicitly unsigned while that key is unprovisioned - never a fabricated signature). Verify with verify_report. The signature proves what was checked and when, not that the site is good.

  • site_audit_summaryFree

    Free. Submit a site URL; the worker runs 12 agent-legibility checks against it (robots.txt AI-crawler directives, llms.txt, MCP advertisement, structured data, meta/charset/content-type sanity, no-JS response) with bounded fetches, private addresses refused, and a per-target rate limit. Returns how many of 12 passed, plus target and date - enough to decide whether the paid per-check detail is worth it.

  • site_audit_x402Free

    Paid ($0.25, x402/USDC). Same full site audit as site_audit: all 12 checks with status and detail as a signed dated receipt. Pay with x402 if you hold USDC; use site_audit to pay by card or other MPP methods. Payment settles before the target is checked, so run the free site_audit_summary first to confirm your URL is valid and not rate limited.

  • verify_reportFree

    Free. Verify a report receipt's Ed25519 signature, and optionally check that a findings array matches the hash the receipt committed to. Use this before paying to confirm the seller is describing real work, and after paying to confirm you received all of it.

Public scan report

scanner v0.1.10 · 2026-10-30 · same rubric, same numbers if you re-run it

no findings
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 3564ms17/20
  • Tool poisoning10 tool descriptions checked15/15
  • Auth qualityopen endpoint, read-only tools10/15
  • Maintenancelast push 44 days ago12/15
  • Maintainer identityregistry namespace matches repository owner6/10
Overall 80/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Course Drift Oracle compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
80/100
higher than 60% of 48,255 servers
Tools
10
the typical server has 7
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
Uptime
100%
of our recent checks; the typical remote server answers 100%
Response time
1,583 ms
faster than 5% of 30,031 servers

What its tools let an agent do: 10 read

Install Course Drift Oracle in Claude Code, Cursor or VS Code

claude mcp add --transport http course-drift-oracle https://signetworks.atelieri.workers.dev/mcp
Add to Cursor

What the publisher says

From the Course Drift Oracle repository's README, as published. We do not edit it. Read it on GitHub

Course Drift Oracle

A signed drift report for Microsoft's ai-agents-for-beginners course. It scans the course for two things that go wrong quietly:

retire

  • model pins that name a deployment which is deprecated or scheduled to

newer major version than the course was written against

  • package version floors whose open >= requirement now resolves to a

Both are invisible in a diff. Nothing in a course repo tells you a pinned model is about to stop serving, or that pip install today pulls a package two majors ahead of what the lessons assume. Answering that question takes someone actually checking each pin against the platform's own retirement calendar and the package's real release history. This repository does that checking, continuously, and sells the result as a signed report.

Why trust it

Every report is signed, not just asserted:

were signed can be reconstructed and re-hashed by anyone, in any language. A Python-signed receipt verifies against the TypeScript verifier with no shared trust between them - see oracle/receipt.py (signs) and worker/src/logic.ts (verifies).

  • Ed25519 signatures over RFC 8785 canonical JSON. The exact bytes that

in oracle/chain.jsonl, each entry pointing at the hash of the one before it. Drop an entry, edit one, or reorder two and every later link stops matching. oracle/verify_chain.py checks this independently of the code that writes it.

  • Append-only publication chain. Every report ever published is a link

summary's claims are backed by a real signature, and after paying to confirm the paid report matches the hash the free summary already committed to. A seller who serves fewer findings than promised gets caught by arithmetic, not by trust.

  • verifyreport is free.** Call it before paying to confirm the free

product; it is the product's actual scanner, signing code, and server, in the same form that runs the live service.

  • This repository is the source. Nothing here is a description of the

Use it in five minutes

The service is an MCP server over streamable HTTP:

https://signetworks.atelieri.workers.dev/mcp

Copy-paste quickstart, plain curl, no client library (every command here was run against production before being written down):

# 1. Initialize and capture the session id from the response headers.
SESSION_ID=$(curl -si -X POST https://signetworks.atelieri.workers.dev/mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"quickstart","version":"1.0"}}}' \
  | tr -d '\r' | awk 'tolower($1)=="mcp-session-id:"{print $2}')

# 2. Complete the handshake.
curl -s -X POST https://signetworks.atelieri.workers.dev/mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -H "Mcp-Session-Id: $SESSION_ID" \
  -d '{"jsonrpc":"2.0","method":"notifications/initialized"}'

# 3. Call a free tool. Responses are SSE frames; strip the data: prefix.
curl -s -X POST https://signetworks.atelieri.workers.dev/mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -H "Mcp-Session-Id: $SESSION_ID" \
  -d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"drift_summary","arguments":{}}}' \
  | grep '^data:' | sed 's/^data: //'

The same pattern calls every tool in the table above; only the name and arguments change.

Ten tools:

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Course Drift Oracle: common questions

Is Course Drift Oracle MCP server safe?
Mostly: it is graded B (80/100). Read the Course Drift Oracle safety report
How do I install Course Drift Oracle?
It runs remotely at signetworks.atelieri.workers.dev. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Course Drift Oracle need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Course Drift Oracle maintained?
The last commit was 49 days ago (2026-09-16). The latest release is v1.0.0.
Is Course Drift Oracle up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
How does Course Drift Oracle compare with other MCP servers?
safety score 80/100 (higher than 60% of 48,255 servers); tools 10 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.