Nostr Bray MCP Server
nostr-bray
npm
v3.4.2
Source verified
Published by forgesworn — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
Trust-aware Nostr for AI and humans. Three dimensions of trust -- verification, proximity, and access -- woven into every interaction.
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 10 = 90. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −10 | capability blast radius (critical) — client exposure if the model is manipulated |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 7
critical Completed toxic-flow trifecta across toolsMTC-FLOW-002
This server (without client built-ins) exposes a complete data-exfiltration chain: article-read → trust-spoken-challenge → handler-publish. Untrusted input is ingested, private data is read, and it can be sent to an external sink via the agent composing the tools (→). Static analysis proves the primitive exists, not that a specific run will occur.
Fix: Remove one leg of the trifecta: isolate untrusted-input tools from secret-reading tools and from egress tools, or require human approval between them.
Location: flow article-read → trust-spoken-challenge → handler-publish
high Tool "handler-publish" exposes command/code executionMTC-CAP-001
Tool "handler-publish" appears to run shell commands or evaluate code (parameter "command"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool handler-publish
medium Hardcoded egress to an external endpoint (dist/util/handlers.js)MTC-SRC-003
In the server's implementation (`dist/util/handlers.js:288`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const response = await fetch('https://raw.githubusercontent.com/nostr-protocol/nips/master/README.md', { signal
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/util/handlers.js
medium Unconstrained URL/host parameter "url" on "marketplace-probe"MTC-CAP-007
Tool "marketplace-probe" takes a URL/host parameter "url" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).
Fix: Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.
Location: tool marketplace-probe · inputSchema.properties.url
medium Unconstrained URL/host parameter "url" on "relay-info"MTC-CAP-007
Tool "relay-info" takes a URL/host parameter "url" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).
Fix: Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.
Location: tool relay-info · inputSchema.properties.url
medium Unconstrained command parameter "stdio_command" on "handler-publish"MTC-CAP-006
Tool "handler-publish" takes a command-shaped parameter "stdio_command" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.
Fix: Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.
Location: tool handler-publish · inputSchema.properties.stdio_command
low Mutating tool "handler-publish" declares no destructiveHintMTC-CAP-005
Tool "handler-publish" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool handler-publish
Tools 200
Each tool and what it can reach — statically extracted from the published source.
article-readingests untrusted inputcalendar-readingests untrusted inputcontacts-getingests untrusted inputdm-conversationingests untrusted inputfeed-by-nameingests untrusted inputgroup-chatingests untrusted inputgroup-infoingests untrusted inputhandler-publishruns code / shellhashtag-feedingests untrusted inputidentity-backupingests untrusted input
Show 190 more tools ↓
marketplace-probenetwork egressnip-readingests untrusted inputnip05-relaysingests untrusted inputprivacy-read-proofingests untrusted inputpublish-eventnetwork egressrelay-countingests untrusted inputrelay-infoingests untrusted inputsocial-feedingests untrusted inputsocial-notificationsingests untrusted inputsocial-profile-getingests untrusted inputtrust-spoken-challengereads sensitive datatrust-spoken-verifyreads sensitive dataarticle-listno sensitive capabilityarticle-publishno sensitive capabilitybadge-acceptno sensitive capabilitybadge-awardno sensitive capabilitybadge-createno sensitive capabilitybadge-listno sensitive capabilityblossom-checkno sensitive capabilityblossom-deleteno sensitive capabilityblossom-discoverno sensitive capabilityblossom-listno sensitive capabilityblossom-mirrorno sensitive capabilityblossom-repairno sensitive capabilityblossom-serversno sensitive capabilityblossom-uploadno sensitive capabilityblossom-usageno sensitive capabilityblossom-verifyno sensitive capabilitycalendar-createno sensitive capabilitycalendar-rsvpno sensitive capabilitycanary-beacon-checkno sensitive capabilitycanary-beacon-createno sensitive capabilitycanary-duress-detectno sensitive capabilitycanary-duress-signalno sensitive capabilitycanary-group-createno sensitive capabilitycanary-group-currentno sensitive capabilitycanary-group-joinno sensitive capabilitycanary-group-membersno sensitive capabilitycanary-group-verifyno sensitive capabilitycanary-session-createno sensitive capabilitycanary-session-currentno sensitive capabilitycanary-session-verifyno sensitive capabilitycast-spellno sensitive capabilitycommunity-approveno sensitive capabilitycommunity-createno sensitive capabilitycommunity-feedno sensitive capabilitycommunity-listno sensitive capabilitycommunity-postno sensitive capabilitycontacts-followno sensitive capabilitycontacts-searchno sensitive capabilitycontacts-unfollowno sensitive capabilitydispatch-ackno sensitive capabilitydispatch-cancelno sensitive capabilitydispatch-capability-discoverno sensitive capabilitydispatch-capability-publishno sensitive capabilitydispatch-capability-readno sensitive capabilitydispatch-checkno sensitive capabilitydispatch-failureno sensitive capabilitydispatch-proposeno sensitive capabilitydispatch-queryno sensitive capabilitydispatch-refuseno sensitive capabilitydispatch-replyno sensitive capabilitydispatch-sendno sensitive capabilitydispatch-statusno sensitive capabilitydm-by-nameno sensitive capabilitydm-readno sensitive capabilitydm-sendno sensitive capabilityexecute-actionno sensitive capabilitygroup-add-userno sensitive capabilitygroup-adminsno sensitive capabilitygroup-createno sensitive capabilitygroup-deleteno sensitive capabilitygroup-delete-eventno sensitive capabilitygroup-forum-commentno sensitive capabilitygroup-forum-commentsno sensitive capabilitygroup-forum-topic-createno sensitive capabilitygroup-forum-topicsno sensitive capabilitygroup-inspectno sensitive capabilitygroup-invite-createno sensitive capabilitygroup-joinno sensitive capabilitygroup-leaveno sensitive capabilitygroup-membersno sensitive capabilitygroup-remove-userno sensitive capabilitygroup-rolesno sensitive capabilitygroup-sendno sensitive capabilitygroup-updateno sensitive capabilityhandler-discoverno sensitive capabilityidentity-accept-migrationno sensitive capabilityidentity-backup-shamirno sensitive capabilityidentity-createno sensitive capabilityidentity-deriveno sensitive capabilityidentity-derive-personano sensitive capabilityidentity-listno sensitive capabilityidentity-migrateno sensitive capabilityidentity-proveno sensitive capabilityidentity-restoreno sensitive capabilityidentity-restore-shamirno sensitive capabilityidentity-switchno sensitive capabilitylabel-createno sensitive capabilitylabel-readno sensitive capabilitylabel-removeno sensitive capabilitylabel-searchno sensitive capabilitylabel-selfno sensitive capabilitylist-bookmarkno sensitive capabilitylist-bookmark-readno sensitive capabilitylist-check-mutedno sensitive capabilitylist-followset-createno sensitive capabilitylist-followset-manageno sensitive capabilitylist-followset-readno sensitive capabilitylist-muteno sensitive capabilitylist-mute-readno sensitive capabilitylist-pinno sensitive capabilitylist-pin-readno sensitive capabilitylisting-closeno sensitive capabilitylisting-createno sensitive capabilitylisting-readno sensitive capabilitylisting-searchno sensitive capabilitymarketplace-announceno sensitive capabilitymarketplace-callno sensitive capabilitymarketplace-compareno sensitive capabilitymarketplace-credentials-clearno sensitive capabilitymarketplace-discoverno sensitive capabilitymarketplace-inspectno sensitive capabilitymarketplace-payno sensitive capabilitymarketplace-reputationno sensitive capabilitymarketplace-retireno sensitive capabilitymarketplace-searchno sensitive capabilitymarketplace-updateno sensitive capabilitymoderation-filterno sensitive capabilitynip-publishno sensitive capabilitynip05-lookupno sensitive capabilitynip05-verifyno sensitive capabilitypost-queue-cancelno sensitive capabilitypost-queue-listno sensitive capabilitypost-scheduleno sensitive capabilityprivacy-commitno sensitive capabilityprivacy-openno sensitive capabilityprivacy-prove-ageno sensitive capabilityprivacy-prove-rangeno sensitive capabilityprivacy-prove-thresholdno sensitive capabilityprivacy-publish-proofno sensitive capabilityprivacy-verify-ageno sensitive capabilityprivacy-verify-rangeno sensitive capabilityprivacy-verify-thresholdno sensitive capabilityprofile-by-nameno sensitive capabilityrelay-addno sensitive capabilityrelay-authno sensitive capabilityrelay-compareno sensitive capabilityrelay-discoverno sensitive capabilityrelay-diversityno sensitive capabilityrelay-listno sensitive capabilityrelay-nip-searchno sensitive capabilityrelay-queryno sensitive capabilityrelay-recommendno sensitive capabilityrelay-setno sensitive capabilitysafety-activateno sensitive capabilitysafety-configureno sensitive capabilitysearch-actionsno sensitive capabilitysearch-notesno sensitive capabilitysearch-profilesno sensitive capabilitysignet-badgeno sensitive capabilitysignet-challengeno sensitive capabilitysignet-credentialsno sensitive capabilitysignet-policy-checkno sensitive capabilitysignet-policy-setno sensitive capabilitysignet-verifiersno sensitive capabilitysignet-vouchno sensitive capabilitysocial-deleteno sensitive capabilitysocial-postno sensitive capabilitysocial-profile-setno sensitive capabilitysocial-reactno sensitive capabilitysocial-replyno sensitive capabilitysocial-repostno sensitive capabilitysync-planno sensitive capabilitytrust-attestno sensitive capabilitytrust-attest-filterno sensitive capabilitytrust-attest-parseno sensitive capabilitytrust-claimno sensitive capabilitytrust-proof-publishno sensitive capabilitytrust-readno sensitive capabilitytrust-requestno sensitive capabilitytrust-request-listno sensitive capabilitytrust-revokeno sensitive capabilitytrust-ring-proveno sensitive capabilitytrust-ring-verifyno sensitive capabilitytrust-verifyno sensitive capabilitywhoamino sensitive capabilitywiki-listno sensitive capabilitywiki-publishno sensitive capabilitywiki-readno sensitive capability
Toxic flows 1
Cross-tool combinations that form a data-exfiltration primitive (untrusted input → sensitive source → external sink).
What this scan could not see
- Tools were statically extracted from the published source (200 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 7
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v3.4.2 latest |
A 90/100 | 7 | 1.13.0 | 2026-09-07 |
v3.3.0 |
A 90/100 | 7 | 1.13.0 | 2026-09-01 |
v3.2.2 |
A 90/100 | 7 | 1.12.1 | 2026-08-23 |
v3.0.0 |
A 90/100 | 7 | 1.12.1 | 2026-08-18 |
v2.4.0 |
A 90/100 | 7 | 1.12.1 | 2026-08-13 |
Show 2 more versions ↓
v2.3.0 |
A 90/100 | 7 | 1.12.1 | 2026-08-07 |
v1.41.0 |
A 90/100 | 7 | 1.12.1 | 2026-07-28 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan nostr-bray --onlineMore in Finance & Commerce
<img src="./public/logo.png" alt="1Money Logo" width="200"/>
Signed verification attestations for agent decisions: business, price, freshness, claim checks.
Actual Budget MCP server exposing API functionality
MCP server for Actual Budget - query and manage your personal finances through Claude
The Adyen Model Context Protocol server allows you to integrate with Adyen APIs through LLMs function calling utilizing various Clients. It currently supports the following tools:
Trusted agent-commerce hub: discover, trust-check, and route x402 payments with failover.