Sentinel
REMOTE · 448C.ORG
Pay-per-call safety checks for AI agents: screen a crypto address or URL before you transact.
Available components
Last scanned (16 hours ago)
Scores higher than 66% of remote servers
Reachable. Last reached 5 Nov 2026.
Category Security
Recent critical change
Authorization (29 Oct 2026). See the changelog before you install this server.
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security57
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (storage_replace). See how to fix → View diagnostics → Fail
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability64
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 12686 tokens (~243/item across 52 items; 52 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (4% of tools); any adoption earns full credit.Pass
Tool Safety90
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 3 of 5 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "pay_requirements" implies "pay" and declares readOnlyHint instead, contradicting what its own name says it does. See how to fix → Partial
- An AI judge read all 52 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Checks we ran (13)
- TLS certificate
- Authorization
- HTTPS
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 5 Nov 26 0
- New tool “rpc_call” functional
- 4 Nov 26 0
- New tool “relay_usdc” functional
- 30 Oct 26 0
- A breaking change shipped without a version bump: still 0.1.0 ▼ security
- Tool “free_inbox” was removed ▼ security
- 29 Oct 26 −10
- Authorization: partial → fail ▼ critical
- The server changed its declared name: mcp-typescript server on vercel → agent-exec security
- New tool “claim_release”, which the server declares destructive security
- New tool “dns_release”, which the server declares destructive security
- New tool “placement_cancel”, which the server declares destructive security
- New tool “release_inbox”, which the server declares destructive security
- New tool “storage_delete”, which the server declares destructive security
- New tool “storage_replace”, which the server declares destructive security
- Tool “check_address” rewrote its description, which is the text the model reads security
- Tool “check_url” rewrote its description, which is the text the model reads security
- Schema quality: pass → fail ▼ functional
- The server now declares the “prompts” capability functional
- The server now declares the “resources” capability functional
- First check of Tool coverage: 4 functional
- Destructive annotations: pass → 60 functional
- New tool “attest_create” functional
- New tool “attest_read” functional
- New tool “claim_acquire” functional
- New tool “claim_acquire_free” functional
- New tool “claim_read” functional
- New tool “claim_renew” functional
- New tool “create_inbox” functional
- New tool “deadman_confirm” functional
- New tool “deadman_read” functional
- New tool “deadman_register” functional
- New tool “dns_lookup” functional
- New tool “dns_renew” functional
- New tool “dns_rent” functional
- New tool “dns_rent_free” functional
- New tool “dns_set_records” functional
- New tool “drift_baseline” functional
- New tool “drift_check” functional
- New tool “drift_venues” functional
- New tool “execute” functional
- New tool “free_inbox” functional
- New tool “handoff_deposit” functional
- New tool “handoff_read” functional
- New tool “inbox_status” functional
- New tool “listing_promote” functional
- New tool “pay_receipt” functional
- New tool “pay_requirements” functional
- New tool “pay_send” functional
- New tool “placement_order” functional
- New tool “placement_ready” functional
- New tool “placement_status” functional
- New tool “placement_venues” functional
- New tool “read_inbox” functional
- New tool “search_listings” functional
- New tool “service_card” functional
- New tool “storage_buy” functional
- New tool “storage_list” functional
- New tool “storage_read” functional
- New tool “storage_renew” functional
- New tool “storage_usage” functional
- New tool “watch_read” functional
- New tool “watch_register” functional
- New tool “x402_supported” functional
- New tool “x402_verify” functional
- “check_address” reworded the description of “address” cosmetic
- “check_address” reworded the description of “chain” cosmetic
- “check_url” reworded the description of “url” cosmetic
- Tool “check_address” changed its title: Check an EVM address against public risk feeds (paid, x402) cosmetic
- Tool “check_url” changed its title: Check a URL against public risk feeds (paid, x402) cosmetic
- 28 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 26 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Aug 26 0
- Stability: 0.97 → pass security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Probed https://448c.org/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=448c.org | CN=YE1,O=Let's Encrypt,C=US | 29 Oct 2026 | 27 Jan 2027 | ECDSA 256 | ECDSA-SHA384 | 59e5032cc568aee114bcc23674041144243 |
| SANs: 448c.org | ||||||
| CN=YE1,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 5ddd70dd31f801c85c186a7a04b80afe |
| CN=Root YE,O=ISRG,C=US (CA) | CN=ISRG Root X2,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | ECDSA-SHA384 | 872165fc34b6e5fba8add5b3705fb53a |
| CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | SHA256-RSA | 6c8f1dc727c7117f7baf853ac980f9cd |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of 448c.org. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| org. | DS published | 725, 26974 | 8, 8 | Verified |
| 448c.org. | No DS | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://448c.org/mcp | Verified | 200 | |
| http (plaintext) | http://448c.org/mcp | HTTPS enforced | 308 | https://448c.org/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
x402_supported x402 facilitator: the kinds this service accepts (free) ~132
FREE and unauthenticated: the x402 facilitator read contract -- {kinds:[{x402Version, scheme, network, extra?}]}, folded out of the same document GET /.well-known/x402.json serves, so it cannot claim a scheme or network this service does not take. This is the tool form of GET /supported on this host. No payment, no key, no RPC. Complaints, questions, quote requests, or a service you wish we had: POST /feedback on this host -- free, no account. Every report is read and analysed daily; there is no individual reply.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
x402_verify x402 facilitator: verify an EVM exact payment offline (free) ~273
FREE and unauthenticated: check an EVM `exact` x402 payment OFFLINE and get back {isValid, invalidReason?, payer?, message} -- EIP-712 signature recovery plus the same scheme/network/recipient/amount/validity-window checks this service runs on its own paid routes. It does NOT read the payer's on-chain balance or nonce (no chain connection here), so isValid is not a promise that settlement succeeds; message says so. A Solana payload is refused explicitly rather than called invalid. Settlement (/settle) is deliberately not offered: broadcasting a transaction spends gas. This is the tool form of POST /verify on this host. Complaints, questions, quote requests, or a service you wish we had: POST /feedback on this host -- free, no account. Every report is read and analysed daily; there is no individual reply.
| Name | Type | Req | Description |
|---|---|---|---|
| paymentPayload | object | yes | The x402 PaymentPayload you signed: {x402Version, scheme, network, payload:{signature, authorization:{...}}}. |
| paymentRequirements | object | yes | The PaymentRequirements the payment was signed against: {scheme, network, maxAmountRequired, payTo, asset, ...}. |
| x402Version | integer | – | Protocol version of the verify request itself; defaults to 1. |
No output schema declared.
No examples provided.
How do I install the Sentinel MCP server?
Sentinel is a hosted endpoint at https://448c.org/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · 448c.org
claude mcp add --transport http org-448c-sentinel 'https://448c.org/mcp'
What is the Sentinel MCP server?
Sentinel is an MCP server listed in the public MCP registry as org.448c/sentinel. Pay-per-call safety checks for AI agents: screen a crypto address or URL before you transact. This page covers its hosted endpoint (https://448c.org/mcp).
Is the Sentinel MCP server safe to use?
Sentinel scores 76 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Sentinel MCP server expose?
Sentinel exposes 52 tools: execute, storage_buy, storage_renew, storage_replace, storage_read, and 47 more. Their descriptions and schemas cost roughly 12,686 tokens of context every time the server is loaded.
Does the Sentinel MCP server require authentication?
No. We connected to Sentinel without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Sentinel MCP server still maintained?
Sentinel is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What did VerifyMCP test on the Sentinel MCP server?
VerifyMCP ran 13 checks on Sentinel, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.