Second Eyes Agent Workflow Services
NPM · @SECONDEYES/MCP-UNBLOCK · 2 COMPONENTS · SCANNED SEP 20
Workflow diagnostics, capability routing, and x402 settlement for MCP-compatible agents.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security99
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 31 of 114 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency71
- Repository check failed: the declared repository URL redirects; it must resolve directly. See how to fix → View diagnostics → Fail
- Cryptographically verified build provenance (signed, bound to This-Is-Hellgate/second-eyes-ai). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 74 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability78
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 1286 tokens (~116/item across 11 items; 11 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 Management97
- Stability observed for 29 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage89
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 60% of tool parameters carry a description.Partial
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 11 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 11 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
How do I install the Second Eyes Agent Workflow Services MCP server?
Second Eyes Agent Workflow Services runs locally as an npm package, launched with npx -y @secondeyes/mcp-unblock. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @secondeyes/mcp-unblock
claude mcp add this-is-hellgate-secondeye-mcp-unblock -- npx -y @secondeyes/mcp-unblock
{
"mcpServers": {
"this-is-hellgate-secondeye-mcp-unblock": {
"command": "npx",
"args": [
"-y",
"@secondeyes/mcp-unblock"
]
}
}
} {
"servers": {
"this-is-hellgate-secondeye-mcp-unblock": {
"command": "npx",
"args": [
"-y",
"@secondeyes/mcp-unblock"
]
}
}
} codex mcp add this-is-hellgate-secondeye-mcp-unblock -- npx -y @secondeyes/mcp-unblock
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"this-is-hellgate-secondeye-mcp-unblock": {
"type": "local",
"command": [
"npx",
"-y",
"@secondeyes/mcp-unblock"
],
"enabled": true
}
}
} openclaw mcp add this-is-hellgate-secondeye-mcp-unblock --command npx --arg -y --arg @secondeyes/mcp-unblock
mcp_servers:
this-is-hellgate-secondeye-mcp-unblock:
command: "npx"
args: ["-y", "@secondeyes/mcp-unblock"] {
"McpServers": {
"this-is-hellgate-secondeye-mcp-unblock": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"@secondeyes/mcp-unblock"
]
}
}
} assistant mcp add this-is-hellgate-secondeye-mcp-unblock -t stdio -c npx -a -y @secondeyes/mcp-unblock
{
"mcpServers": {
"this-is-hellgate-secondeye-mcp-unblock": {
"command": "npx",
"args": [
"-y",
"@secondeyes/mcp-unblock"
]
}
}
} 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.
- 20 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 19 Sept 26 −5
- Source repository: pass → fail ▼ security
- 18 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 16 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 15 Sept 26 −3
- Stability: pass → 0.80 functional
- 14 Sept 26 0
- Stability: 0.97 → pass security
- 13 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 11 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
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 20 Sept 2026 · Analysed npm/@secondeyes/mcp-unblock@1.2.7
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | This-Is-Hellgate/second-eyes-ai |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/This-Is-Hellgate/second-eyes-ai/.github/workflows/publish-mcp.yml@refs/tags/mcp-v1.2.7 |
| Rekor log index | 2107133845 |
| Predicate type | https://slsa.dev/provenance/v1 |
| Subject digest | sha512:1d1c192dc64d36f8eb4b5a15a22dd85e7b0628b6258abacbd40419bd540a80f1457db145fe922ee563354cbd583e24f1059ebc6c76368b69e362d4346 |
Background: How many MCP packages publish verified provenance →
Dependencies 114 packages
| Packages resolved | 114 |
|---|---|
| Stale | 31 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
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 →
enter_lounge Create workflow session ~83
Free. Open a compatibility session and receive a session_id required by pause_and_route and order_service. Supply a stable agent_id you control. Returns session.id, your patron mark, and session headers. Call after proof_bar confirms the service is live. Sessions expire after 120s of inactivity — keep them short.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | Stable agent identifier |
| Name | Type | Req | Description |
|---|---|---|---|
| session_header | string|null | – | – |
| status | number | – | – |
No examples provided.
fetch_catalog Full catalog ~68
Free, read-only. Retrieve the full capability catalogue including the extended tiers beyond the standard menu: nano taps ($0.05), micro taps ($0.25), and tool packs ($1.00). Use when read_menu is not sufficient and you need all available slugs across every pricing tier.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| status | number | – | – |
No examples provided.
github_mcp_401_fix github-mcp 401 fix shortcut ~130
Shortcut for a specific failure: github-mcp returning 401 after a PAT is configured. Automatically routes through pause_and_route then orders the mcp-wiring capability ($0.05 USDC), which returns the full PAT scope, stdio path, and SSE wiring guide. Requires a session_id from enter_lounge. Auto-settles payment when MCP_X402_WALLET_KEY is set on the MCP server process; otherwise returns the 402 body with REST payment instructions.
| Name | Type | Req | Description |
|---|---|---|---|
| error_detail | string | – | – |
| session_id | string | yes | session.id from enter_lounge |
| Name | Type | Req | Description |
|---|---|---|---|
| service_status | number | – | – |
| status | number | – | – |
No examples provided.
leave_with_receipt Leave with receipt ~86
Free. Close the current compatibility session and receive an itemized receipt listing all capabilities ordered, total USDC spent, session duration, and grant IDs for each purchase. Call at the end of every workflow. The receipt is the only record of the session — Second Eyes retains no task content after the session closes.
| Name | Type | Req | Description |
|---|---|---|---|
| session_id | string | yes | session.id from enter_lounge |
| Name | Type | Req | Description |
|---|---|---|---|
| status | number | – | – |
No examples provided.
order_service Execute workflow capability (paid) ~419
COSTS USDC (Base) — launch pricing $0.01–$0.05 per call (max $0.05). Order a workflow capability by slug. Compatibility path: proof_bar → enter_lounge (get session_id) → order_service. Paid slugs return HTTP 402; if MCP_X402_WALLET_KEY is set on the MCP server process the payment auto-settles inline via x402 v2 (USDC on Base eip155:8453) and the tool returns the paid result with paid_via_mcp_x402:true. If no wallet is configured the tool returns the 402 body with x402_error.code and REST retry instructions. Autopay-default slugs (zero-arg, convert to a paid 200): loop-detect | scope-check | context-recover | tool-verify | cascade-break | pitstop | pre-run-context | claim-check | context-compress | mcp-wiring | should-i-pay | receipt | help-me | schema-repair. Excluded from zero-arg autopay because they need a caller-supplied input this tool cannot pass: transcribe-extract | doc-extract — call /api/bar/x402/transcribe and /api/bar/x402/extract directly with the required input (a blind order_service retry would reach the door and dead-end on no_input).
| Name | Type | Req | Description |
|---|---|---|---|
| session_id | string | yes | session.id from enter_lounge (carried as X-Second-Eye-Session) |
| slug | string | yes | Zero-arg autopay slug, each ≤ $0.05 USDC: loop-detect | scope-check | context-recover | tool-verify | cascade-break | pitstop | pre-run-context | claim-check | context-compress | mcp-wiring | should-… |
| Name | Type | Req | Description |
|---|---|---|---|
| paid_via_mcp_x402 | boolean | – | true when the wallet auto-settled the 402 |
| payment | object | – | – |
| payment_required | boolean | – | – |
| status | number | yes | 200 when paid/served, 402 when payment could not be completed |
| x402_error | object | – | – |
No examples provided.
patron_activity Execution activity ~63
Free, read-only. Check whether other agents have successfully purchased from Second Eyes and view their on-chain transaction receipts on Base. Use before spending to confirm the payment rail has real settlement history. Returns agent count, purchase count, and recent Base transaction hashes you can verify independently.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| status | number | – | – |
No examples provided.
pause_and_route Pause and route ~134
Free, once per session. Describe a stuck or failed state and receive a routing verdict: which capability slug to call next and why. Input your current task, state description, and failure count. Output is a recommended slug (e.g. mcp-wiring, loop-detect, claim-check) to pass to order_service. Use when you know something is wrong but not which service fixes it. Requires a session_id from enter_lounge.
| Name | Type | Req | Description |
|---|---|---|---|
| failure_count | number | – | – |
| session_id | string | yes | session.id from enter_lounge |
| state | string | – | – |
| task | string | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| status | number | – | – |
No examples provided.
proof_bar Service proof ~72
Free, read-only. Verify the Second Eyes service is live and the x402 Base payment rail is active before spending any USDC. Returns pass:true with per-rail evidence. Run this first — if pass is false, no paid call will succeed. Recommended starting point before enter_lounge or any order_service call.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| pass | boolean | – | – |
| status | number | – | – |
No examples provided.
read_laws Service policies ~68
Free, read-only. Read the deterministic rules that govern every session: idle timeout (120s), free window (15 min), strike policy, session limits, and spend caps. Reference when a session behaves unexpectedly or before building an automated workflow that holds a session open across multiple order_service calls.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| status | number | – | – |
No examples provided.
read_menu Capability catalogue ~83
Free, read-only. List all 12 recovery and verification capabilities available for purchase, each priced $0.01–$0.05 USDC on Base. Each item maps a named agent failure state (looping, blocked, overloaded, uncertain, about to pay) to its slug and exact price. Call before order_service to confirm the right slug for your situation.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| status | number | – | – |
No examples provided.
read_pricing Pricing ~80
Free, read-only. Get the session time pricing curve (free for the first 15 minutes, then $0.10–$2.00/min compounding) plus the per-capability prices for all slugs. Use to calculate maximum cost exposure before enter_lounge, especially when operating under a strict spend cap or planning a long-running session.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| status | number | – | – |
No examples provided.
What is the Second Eyes Agent Workflow Services MCP server?
Second Eyes Agent Workflow Services is an MCP server listed in the public MCP registry as io.github.This-Is-Hellgate/secondeye-mcp-unblock. Workflow diagnostics, capability routing, and x402 settlement for MCP-compatible agents. This page covers its npm package (@secondeyes/mcp-unblock).
Is the Second Eyes Agent Workflow Services MCP server safe to use?
Second Eyes Agent Workflow Services scores 89 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. 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 Second Eyes Agent Workflow Services MCP server expose?
Second Eyes Agent Workflow Services exposes 11 tools: proof_bar, patron_activity, read_menu, read_laws, read_pricing, and 6 more. Their descriptions and schemas cost roughly 1,286 tokens of context every time the server is loaded.
Is the Second Eyes Agent Workflow Services MCP server still maintained?
Second Eyes Agent Workflow Services is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Second Eyes Agent Workflow Services MCP server under?
Second Eyes Agent Workflow Services declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.