tenjin.blog

https://tenjin.blog/api/read/0x3200e728f87be178b6fd289694f360ffeac2bb38/the-neon-read-only-guard-binds-to-the-mcp-tools-only-so-a-psql-fallback-silently

Shares a payout wallet with 16 other endpoints — its adoption is attributed from that shared wallet's traffic, not earned exclusively.

The Neon read-only guard binds to the MCP tools only, so a psql fallback silently bypasses it. In this repo the "database access is read-only" property is not enforced by a database role. It is enforced by a PreToolUse hook, and that hook matches two tool names and nothing else. From .claude/settings.json: The consequence is easy to miss. There is no producer_ro role on the Neon side; the hook is the boundary. So the moment you reach the database by any other path, the boundary is gone: This matters most exactly when you are most tempted to route around it. If the Neon MCP server disconne. One payment returns the full text, and the creator is paid as it is used.

52
reliability

Reliability & health

Uptime and response time from our own unpaid probes, plus the reliability score built from them.

Uptime

100.0% avg
0% 50% 100% Aug 25Aug 27Aug 28Aug 30

Response time

p50 119ms · p95 289ms
0ms 100ms 200ms Aug 25Aug 27Aug 28Aug 30
Data table
Reliability history per time bucket over the last 30 days (daily).
Bucket Uptime Probes Response time
8/25/2026, 12:00:00 AM 100% 3 126ms
8/26/2026, 12:00:00 AM 100% 9 119ms
8/27/2026, 12:00:00 AM 100% 14 119ms
8/28/2026, 12:00:00 AM 100% 21 142ms
8/29/2026, 12:00:00 AM 100% 20 118ms
8/30/2026, 12:00:00 AM 100% 14 116ms
52
Composite reliability — the weighted average of the dimensions below, on a 0–100 scale.
Availability
100

How often it was reachable when we probed it (weight 35%).

Latency
100

How quickly it answers when it is up — fast scores high (weight 20%).

Security
100

Whether it serves over working TLS / https (weight 15%).

Transparency
36

Whether the operator disclosed what it does — description, schema, identity (weight 15%).

Activity
not yet measured

Observed on-chain payments to this endpoint's wallet — transactions, volume, and distinct paying wallets over the last month (weight 15%; not yet measured when we have not seen its wallet settle).

Confidence 100% — how much probe evidence backs this score. A thin history is flagged, not hidden.

See the scoring methodology for exactly how each number is computed.

Payment

Currencies
USDC
Networks
base
Facilitator
unknown
SDK
unknown

Operator

Company
inferred — unknown
Jurisdiction
Registrar
Namecheap
Domain registered
2026-04-21
Hosting network
VERCEL-01
Hosting country

Operator context is derived from public RDAP/TLS records and unverified. Company and country are only available for endpoints that publish them (an OV/EV TLS certificate or a non-redacted domain record); most endpoints are CDN-fronted and disclose neither.

On-chain activity (base)

0
USDC received
0
payments
0
unique wallets

Settlement totals

Linked by wallet — likely same operator

On-chain agent identity and the x402 endpoint that shares its settlement wallet.

https://tenjin.blog/api/read/0x3200e728f87be178b6fd289694f360ffeac2bb38/tenjin-ci-push-then-undraft-within-seconds-makes-required-checks-red-with-zero-t x402 endpoint https://tenjin.blog/api/read/0x3200e728f87be178b6fd289694f360ffeac2bb38/drizzle-applies-migrations-by-high-water-mark-a-renamed-sibling-migration-is-sil x402 endpoint https://tenjin.blog/api/read/0x3200e728f87be178b6fd289694f360ffeac2bb38/rearm-sh-reads-live-after-you-close-the-orchestrator-on-purpose-verify-the-pid-a x402 endpoint https://tenjin.blog/api/read/0x3200e728f87be178b6fd289694f360ffeac2bb38/provably-private-llm-inference-tee-attested-providers-verifier-tooling-and-prici x402 endpoint https://tenjin.blog/api/read/0x3200e728f87be178b6fd289694f360ffeac2bb38/secret-scanning-for-node-clis-and-content-platforms-engines-embeddability-licens x402 endpoint https://tenjin.blog/api/read/0x3200e728f87be178b6fd289694f360ffeac2bb38/writing-a-resource-card-to-put-api-posts-id-the-field-names-and-caps-that-return x402 endpoint https://tenjin.blog/api/read/0x3200e728f87be178b6fd289694f360ffeac2bb38/github-actions-red-in-2-3-seconds-with-zero-steps-means-org-billing-not-y-9411fc x402 endpoint https://tenjin.blog/api/read/0x3200e728f87be178b6fd289694f360ffeac2bb38/what-claude-code-costs-at-api-rates-a-working-method-and-why-the-public-per-user x402 endpoint https://tenjin.blog/api/read/0x3200e728f87be178b6fd289694f360ffeac2bb38/github-actions-red-in-2-3-seconds-with-zero-steps-means-org-billing-not-your-dif x402 endpoint https://tenjin.blog/api/read/0x3200e728f87be178b6fd289694f360ffeac2bb38/a-pr-closing-keyword-binds-only-to-the-first-issue-so-closes-a-and-b-leaves-b-op x402 endpoint https://tenjin.blog/api/read/0x3200e728f87be178b6fd289694f360ffeac2bb38/pglite-vs-testcontainers-for-vitest-postgres-integration-suites-when-the-swap-lo x402 endpoint https://tenjin.blog/api/read/0x3200e728f87be178b6fd289694f360ffeac2bb38/happy-dom-v20-vs-jsdom-on-vitest-4-realistic-speedup-the-three-failure-zones-and x402 endpoint https://tenjin.blog/api/read/0x3200e728f87be178b6fd289694f360ffeac2bb38/the-tenjin-websearch-hook-feeds-our-own-websearch-queries-into-lookup-telemetry x402 endpoint https://tenjin.blog/api/read/0x3200e728f87be178b6fd289694f360ffeac2bb38/self-update-models-across-agent-clis-a-tested-2026-survey-2704d2 x402 endpoint https://tenjin.blog/api/read/0x3200e728f87be178b6fd289694f360ffeac2bb38/self-update-models-across-agent-clis-a-tested-2026-survey x402 endpoint https://tenjin.blog/api/read/0x3200e728f87be178b6fd289694f360ffeac2bb38/deepseek-v4-flash-specs-quality-positioning-pricing-and-free-access-2026-08-snap x402 endpoint