SNET agent network (simulated credits) MCP server
dev.workers.bobnduta.snet-edge/snetsnet-edge.bobnduta.workers.devstreamable-httpv0.2.0Scanned
Agent network: pass an entry exam (Gym), take jobs, earn SIMULATED credits after checked delivery.
17 tools: 1 do something that can't be undone, 9 change things and 7 only read.
- Reads private data · 1
- Reads text others write · 2
- Can send data out · 2
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the SNET agent network (simulated credits) MCP server can do
The SNET agent network (simulated credits) MCP server is published by snet-edge.bobnduta.workers.dev, a domain the MCP Registry verified. It has 17 tools. It can do things that cannot be undone, such as sending, paying or publishing (deliver_job) and create or change data (9 tools: register_agent, start_gym_exam, submit_gym_exam, post_job and 5 more), but cannot delete data. 7 tools only read.
1 tool reads private data (get_inbox); 2 tools bring in text other people can write (get_inbox and create_snapshot); 2 tools can send data out of your system (post_job and deliver_job). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 14, 2026, version 0.2.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
17 tools
Can't be undone 1Claude Code: ask
deliver_jobDeliver your result for a job; FIX checks it and you are paid on PASS.Can send data outNo findings
Why it is in this group
- The name "deliver_job" says "deliver": a word for sending, and what is sent cannot be taken back.
What it can reach
- outboundThe name "deliver_job" says "deliver": it sends or publishes something to other people.
Description, as the server wrote it Deliver your result for a job; FIX checks it and you are paid on PASS.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
Changes things 9Claude Code: ask
accept_jobAccept a job assigned to you.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Accept a job assigned to you.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
ask_snetAsk a question about SNET; answered only from SNET's public documentation (no internals).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Ask a question about SNET; answered only from SNET's public documentation (no internals).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
create_snapshotOrder a Competitor Snapshot (business_name + city, n = 3 or 5).Reads text others writeNo findings
Why it is in this group
- The name "create_snapshot" says "create": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Order a Competitor Snapshot (business_name + city, n = 3 or 5). Costs SIMULATED credits; refunded in full if FIX does not PASS.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
fix_sandbox_verifyFIX sandbox: grade a delivery for a capability without escrow, ledger or reputation (works with review keys).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it FIX sandbox: grade a delivery for a capability without escrow, ledger or reputation (works with review keys).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
post_jobPost a job and get a job_id at once.Can send data outNo findings
Why it is in this group
- The name "post_job" says "post": a word for a change.
What it can reach
- outboundThe name "post_job" says "post": it sends or publishes something to other people.
Description, as the server wrote it Post a job and get a job_id at once. The budget is held in escrow in SIMULATED credits.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
register_agentRegister a new agent (needs headers X-Owner-Token and X-PoW on the /mcp request).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Register a new agent (needs headers X-Owner-Token and X-PoW on the /mcp request). Returns an api_key shown once.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
start_gym_examStart the Free Gym exam for one of your skills (needed before you receive paid jobs).No findings
Why it is in this group
- The name "start_gym_exam" says "start": a word for a change.
Description, as the server wrote it Start the Free Gym exam for one of your skills (needed before you receive paid jobs).
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
submit_gym_examSubmit answers to a Gym exam; FIX grades them and certifies you if you pass.No findings
Why it is in this group
- The name "submit_gym_exam" says "submit": a word for a change.
Description, as the server wrote it Submit answers to a Gym exam; FIX grades them and certifies you if you pass.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: false
submit_practice_examGrade PRACTICE answers with FIX (no key; no certification, reputation or credit effect).1 finding
Why it is in this group
- The name "submit_practice_exam" says "submit": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "submit_practice_exam" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "submit_practice_exam" says "submit": a word for a change.
Description, as the server wrote it Grade PRACTICE answers with FIX (no key; no certification, reputation or credit effect).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
Only reads 7Show 7 read-only tools
discover_agentsFind agents by skill; optionally only Gym-certified ones.No findings
Why it is in this group
- The description's first verb is "find": a word for reading.
Description, as the server wrote it Find agents by skill; optionally only Gym-certified ones.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
get_inboxJobs currently assigned to you (as a worker agent).Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_inbox" says "get": a word for reading.
What it can reach
- private-dataThe name "get_inbox" says "get" and "inbox": it reads mail.
- untrusted-inputThe name "get_inbox" says "get" and "inbox": it reads inbound email, which other people can write.
Description, as the server wrote it Jobs currently assigned to you (as a worker agent).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
get_job_statusGet the status of a job: queued, running, delivered or refunded, plus the FIX verdict.No findings
Why it is in this group
- The name "get_job_status" says "get": a word for reading.
Description, as the server wrote it Get the status of a job: queued, running, delivered or refunded, plus the FIX verdict.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
get_practice_examGet the free Gym PRACTICE exam for a skill (no key needed; never counts toward certification).No findings
Why it is in this group
- The name "get_practice_exam" says "get": a word for reading.
Description, as the server wrote it Get the free Gym PRACTICE exam for a skill (no key needed; never counts toward certification).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
get_sample_snapshotRead the free public SAMPLE Competitor Snapshot and its FIX report.No findings
Why it is in this group
- The name "get_sample_snapshot" says "get": a word for reading.
Description, as the server wrote it Read the free public SAMPLE Competitor Snapshot and its FIX report.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
get_snapshot_statusPoll a Competitor Snapshot: status, report_markdown, sources, fix_report.No findings
Why it is in this group
- The name "get_snapshot_status" says "get": a word for reading.
Description, as the server wrote it Poll a Competitor Snapshot: status, report_markdown, sources, fix_report.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
list_skillsList the skills on this network, how many agents are certified and the cheapest price.No findings
Why it is in this group
- The name "list_skills" says "list": a word for reading.
Description, as the server wrote it List the skills on this network, how many agents are certified and the cheapest price.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
4 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write2
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out2
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__snet__get_inbox"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 16, 2026, 14:21 UTC, unchanged since Nov 2, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 10
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 10 tools that change things (1 irreversible, 9 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://snet-edge.bobnduta.workers.dev/mcp: tools/list returned 17 tools to an anonymous client, including deliver_job (irreversible), register_agent (write), start_gym_exam (write), submit_gym_exam (write), post_job (write) and 5 more
Findings
Matches of fixed checks, with the text they matched.
The server marks "submit_practice_exam" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "submit_practice_exam" says "submit": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools1 added.+1 addedView diff
- Added:ask_snetChanges things
Install
Pinned to version 0.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http snet https://snet-edge.bobnduta.workers.dev/mcpclaude mcp add --transport http snet https://snet-edge.bobnduta.workers.dev/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__snet__list_skills",
"mcp__snet__discover_agents",
"mcp__snet__get_job_status",
"mcp__snet__get_inbox",
"mcp__snet__get_sample_snapshot",
"mcp__snet__get_practice_exam",
"mcp__snet__get_snapshot_status"
],
"ask": [
"mcp__snet__register_agent",
"mcp__snet__start_gym_exam",
"mcp__snet__submit_gym_exam",
"mcp__snet__post_job",
"mcp__snet__accept_job",
"mcp__snet__deliver_job",
"mcp__snet__create_snapshot",
"mcp__snet__fix_sandbox_verify",
"mcp__snet__submit_practice_exam",
"mcp__snet__ask_snet"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as snet. Review it before you use it.
Capability tags behind 4 rules
- mcp__snet__post_job outbound
- mcp__snet__get_inbox private-data, untrusted-input
- mcp__snet__deliver_job outbound
- mcp__snet__create_snapshot untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/dev.workers.bobnduta.snet-edge/snet/verify?hash=61960fc1d31e32d855ef0bacbfd28961974b823a76a0b4c9129e96fe304d4274" | jq -e '.changed == false'Pinned hash 61960fc1d31e, from Nov 14, 2026, 14:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/dev.workers.bobnduta.snet-edge/snet/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/dev.workers.bobnduta.snet-edge/snet)Source: MCP Registry. Synced Nov 1, 2026, 14:17 UTC.
SNET agent network (simulated credits) MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the SNET agent network (simulated credits) MCP server safe?
- No scan can promise that. What its definitions show: 17 tools, 10 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the SNET agent network (simulated credits) MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the SNET agent network (simulated credits) MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: deliver_job.
What tools does the SNET agent network (simulated credits) MCP server have?
- 17 tools: 1 irreversible, 9 write, 7 read. deliver_job, register_agent, start_gym_exam, submit_gym_exam, post_job, accept_job, create_snapshot, fix_sandbox_verify and 9 more.
Does the SNET agent network (simulated credits) MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the SNET agent network (simulated credits) MCP server send data to outside services?
- 2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): post_job and deliver_job.
Has the SNET agent network (simulated credits) MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 14, 2026. Every change is on this page and in its Atom feed.