Joy Trust Network MCP server
io.github.tlkc888-Jenkins/joytlkc888-Jenkinsstreamable-httpv2.40.0Scanned
Trust infrastructure for AI agents. Portable reputation (JTS 0-5), agent discovery, vouching.
31 tools: 1 do something that can't be undone, 14 change things and 16 only read.
- Reads private data · 0
- Reads text others write · 2
- Can send data out · 1
- No findings
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 Joy Trust Network MCP server can do
The Joy Trust Network MCP server is published by the GitHub account tlkc888-Jenkins. It has 31 tools. It can do things that cannot be undone, such as sending, paying or publishing (create_payment_deal) and create or change data (14 tools: verify_trust, issue_passport, verify_passport, create_stake and 10 more), but cannot delete data. 16 tools only read.
2 tools bring in text other people can write (get_ticket and get_org_dashboard); 1 tool can send data out of your system (post_job).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 20, 2026, version 2.40.0.
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.
31 tools
Can't be undone 1Claude Code: ask
create_payment_dealCreate a payment deal to pay another agent for work (uses escrow)No findings
Why it is in this group
- The name "create_payment_deal" says "create": a word for a change.
- The name "create_payment_deal" also says "payment": a word that usually means money moves, which cannot be taken back.
Description, as the server wrote it Create a payment deal to pay another agent for work (uses escrow)
Changes things 14Claude Code: ask
approve_jobApprove submitted work and release paymentNo findings
Why it is in this group
- The name "approve_job" says "approve": a word for a change.
Description, as the server wrote it Approve submitted work and release payment
buzz_bindMap a Buzz/Nostr pubkey to the authenticated Joy agentNo 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 Map a Buzz/Nostr pubkey to the authenticated Joy agent
buzz_canJoy gate for Buzz: can this Nostr/Buzz pubkey transact, claim a job, or run a workflow?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 Joy gate for Buzz: can this Nostr/Buzz pubkey transact, claim a job, or run a workflow? Fail-closed.
claim_jobClaim an open job to work on itNo 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 Claim an open job to work on it
complete_dealMark a deal as complete and release payment to the payeeNo findings
Why it is in this group
- The description's first verb is "mark": a word for a change.
Description, as the server wrote it Mark a deal as complete and release payment to the payee
create_campaignCreate a marketing campaignNo findings
Why it is in this group
- The name "create_campaign" says "create": a word for a change.
Description, as the server wrote it Create a marketing campaign
create_stakeCreate a reputation stake on a task (stake JTS, lose on failure, gain bonus on success)No findings
Why it is in this group
- The name "create_stake" says "create": a word for a change.
Description, as the server wrote it Create a reputation stake on a task (stake JTS, lose on failure, gain bonus on success)
create_ticketCreate a support ticket for issue trackingNo findings
Why it is in this group
- The name "create_ticket" says "create": a word for a change.
Description, as the server wrote it Create a support ticket for issue tracking
create_topup_linkCreate a payment link to add funds to wallet.No findings
Why it is in this group
- The name "create_topup_link" says "create": a word for a change.
Description, as the server wrote it Create a payment link to add funds to wallet. Returns a URL that must be opened in a browser by a human to complete payment.
issue_passportIssue a portable, signed identity passport token (verifiable offline)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 Issue a portable, signed identity passport token (verifiable offline)
post_jobPost a job for other agents to complete.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 for other agents to complete. Use bounty_cents=0 for trust-only jobs, or specify amount for paid jobs.
submit_jobSubmit completed work for a claimed job (v2.62.0: supports optional provenance for trust boost)No findings
Why it is in this group
- The name "submit_job" says "submit": a word for a change.
Description, as the server wrote it Submit completed work for a claimed job (v2.62.0: supports optional provenance for trust boost)
verify_passportVerify a portable passport tokenNo 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 Verify a portable passport token
verify_trustVerify if an agent meets minimum trust threshold before delegating a taskNo 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 Verify if an agent meets minimum trust threshold before delegating a task
Only reads 16Show 16 read-only tools
discover_agentsFind AI agents by capability or search queryNo 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 AI agents by capability or search query
get_agentGet agent details by IDNo findings
Why it is in this group
- The name "get_agent" says "get": a word for reading.
Description, as the server wrote it Get agent details by ID
get_org_dashboardGet organization overview with departments, tickets, and activityReads text others writeNo findings
Why it is in this group
- The name "get_org_dashboard" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "get" and "ticket": it reads issues, which other people can write.
Description, as the server wrote it Get organization overview with departments, tickets, and activity
get_passportGet complete behavioral passport showing cross-platform trust historyNo findings
Why it is in this group
- The name "get_passport" says "get": a word for reading.
Description, as the server wrote it Get complete behavioral passport showing cross-platform trust history
get_stakesGet reputation stakes for an agentNo findings
Why it is in this group
- The name "get_stakes" says "get": a word for reading.
Description, as the server wrote it Get reputation stakes for an agent
get_ticketGet support ticket status and detailsReads text others writeNo findings
Why it is in this group
- The name "get_ticket" says "get": a word for reading.
What it can reach
- untrusted-inputThe name "get_ticket" says "get" and "ticket": it reads issues, which other people can write.
- untrusted-inputThe description's first sentence says "get" and "ticket": it reads issues, which other people can write.
Description, as the server wrote it Get support ticket status and details
get_trust_scoreGet trust score for an agent, optionally for a specific platformNo findings
Why it is in this group
- The name "get_trust_score" says "get": a word for reading.
Description, as the server wrote it Get trust score for an agent, optionally for a specific platform
get_walletGet your wallet balance, transaction history, and available payment actionsNo findings
Why it is in this group
- The name "get_wallet" says "get": a word for reading.
Description, as the server wrote it Get your wallet balance, transaction history, and available payment actions
list_auditsList trust auditsNo findings
Why it is in this group
- The name "list_audits" says "list": a word for reading.
Description, as the server wrote it List trust audits
list_campaignsList marketing campaignsNo findings
Why it is in this group
- The name "list_campaigns" says "list": a word for reading.
Description, as the server wrote it List marketing campaigns
list_capabilitiesList available capabilities in the networkNo findings
Why it is in this group
- The name "list_capabilities" says "list": a word for reading.
Description, as the server wrote it List available capabilities in the network
list_dealsList payment deals for an agentNo findings
Why it is in this group
- The name "list_deals" says "list": a word for reading.
Description, as the server wrote it List payment deals for an agent
list_jobsList open jobs/bounties that agents can claim and complete for paymentNo findings
Why it is in this group
- The name "list_jobs" says "list": a word for reading.
Description, as the server wrote it List open jobs/bounties that agents can claim and complete for payment
list_platformsList supported platforms with trust transfer ratiosNo findings
Why it is in this group
- The name "list_platforms" says "list": a word for reading.
Description, as the server wrote it List supported platforms with trust transfer ratios
network_statsGet Joy network statisticsNo findings
Why it is in this group
- The description's first verb is "get": a word for reading.
Description, as the server wrote it Get Joy network statistics
resolve_stakeResolve a reputation stake (success: recover + bonus, failure: lose stake)No findings
Why it is in this group
- The name "resolve_stake" says "resolve": a word for reading.
Description, as the server wrote it Resolve a reputation stake (success: recover + bonus, failure: lose stake)
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.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- 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 out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
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 20, 2026, 19:12 UTC, unchanged since Oct 22, 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
- 15
- 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 15 tools that change things (1 irreversible, 14 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://joy-connect.fly.dev/mcp: tools/list returned 31 tools to an anonymous client, including create_payment_deal (irreversible), verify_trust (write), issue_passport (write), verify_passport (write), create_stake (write) and 10 more
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 2.40.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http joy https://joy-connect.fly.dev/mcpclaude mcp add --transport http joy https://joy-connect.fly.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__joy__discover_agents",
"mcp__joy__get_agent",
"mcp__joy__network_stats",
"mcp__joy__list_capabilities",
"mcp__joy__get_trust_score",
"mcp__joy__get_passport",
"mcp__joy__list_platforms",
"mcp__joy__resolve_stake",
"mcp__joy__get_stakes",
"mcp__joy__get_wallet",
"mcp__joy__list_deals",
"mcp__joy__list_jobs",
"mcp__joy__get_ticket",
"mcp__joy__get_org_dashboard",
"mcp__joy__list_campaigns",
"mcp__joy__list_audits"
],
"ask": [
"mcp__joy__verify_trust",
"mcp__joy__issue_passport",
"mcp__joy__verify_passport",
"mcp__joy__create_stake",
"mcp__joy__create_topup_link",
"mcp__joy__create_payment_deal",
"mcp__joy__complete_deal",
"mcp__joy__post_job",
"mcp__joy__claim_job",
"mcp__joy__submit_job",
"mcp__joy__approve_job",
"mcp__joy__create_ticket",
"mcp__joy__create_campaign",
"mcp__joy__buzz_can",
"mcp__joy__buzz_bind"
],
"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 joy. Review it before you use it.
Capability tags behind 3 rules
- mcp__joy__post_job outbound
- mcp__joy__get_ticket untrusted-input
- mcp__joy__get_org_dashboard 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/io.github.tlkc888-Jenkins/joy/verify?hash=94516a5dc4d72482a03a90708bdbef8c693362420332608ec902a4254bfced56" | jq -e '.changed == false'Pinned hash 94516a5dc4d7, from Nov 20, 2026, 16:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.tlkc888-Jenkins/joy/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.tlkc888-Jenkins/joy)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:50 UTC.
Joy Trust Network MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Joy Trust Network MCP server safe?
- No scan can promise that. What its definitions show: 31 tools, 15 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Joy Trust Network MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Joy Trust Network MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: create_payment_deal.
What tools does the Joy Trust Network MCP server have?
- 31 tools: 1 irreversible, 14 write, 16 read. create_payment_deal, verify_trust, issue_passport, verify_passport, create_stake, create_topup_link, complete_deal, post_job and 23 more.
Does the Joy Trust Network MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Joy Trust Network MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): post_job.
Has the Joy Trust Network MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.