# MarketNow

> Verify agent credentials, 9 formats, scam domains; search 70k+ MCP servers with auth-gate state.

- name: io.github.alicelabs-llc/marketnow
- version: 1.16.0
- connection class: unknown (unknown)
- trust: 67/100
- quality: 63/100 (needs work)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.alicelabs-llc%2Fmarketnow
- tools: https://api.protogrid.dev/v1/servers/io.github.alicelabs-llc%2Fmarketnow/tools

**Not classified yet.** The remote endpoints have not been probed successfully, or the listing has nothing to connect to.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "marketnow": {
      "type": "http",
      "url": "https://marketnow.site/api/mcp/"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 0
- freshness: 100
- provenance: 90
- drivers: +repository +namespace-matches-repo +website -unreachable(6 failures) +updated-16d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 63/100 (needs work)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-03-26; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: marketnow_translate_credential (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); marketnow_check_domain (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); marketnow_submit_skill (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 1,082 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 25 (weight 15)

- warn `stability.changes`: 20 tool changes in 30 days
- fail `stability.rug_pull`: 3 tools kept their name but changed most of their description in 30 days; review before trusting them

### dependencies: 67 (weight 15)

- pass `deps.known_vulns`: no known advisory in 16 resolved packages
- fail `deps.mcp_sdk_version`: @modelcontextprotocol/sdk 0.5.0 has 1 known advisory (GHSA-w48q-cv73-mx4w); update @modelcontextprotocol/sdk to 1.24.0 or later
- pass `deps.resolvable`: marketnow-mcp@1.15.0 resolved: 16 packages

- tools: 9, about 1,082 tokens to load them all
- tool set hash: 7a1e19aefe3279299bea4785b5dbad86
- tools last changed: 2026-10-10T08:10:27.987Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.alicelabs-llc/marketnow.svg)](https://protogrid.dev/servers/io.github.alicelabs-llc/marketnow)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-10 `marketnow_submit_skill` changed (title, description, inputSchema, annotations)
  - before: Publish a skill to the MarketNow catalog (the write side). The package is validated and Sentinel-scanned (injection patterns, embedded secrets, dangerous APIs, suspicious URLs, typosquat, dedup against the 70k+ catalog) AND its claims are verified live: repo_url must exist (HTTP 200), install must reference a real package on npm/PyPI/crates/Docker Hub. False claims are rejected (422). Accepted skills with real substance (files/code/verifiable repo) are stored in the public auditable queue as certified-L1.5, pending L2 review and catalog merge. Description-only submissions are accepted but never merged. Any pricing model is accepted — free, per-call (x402), subscription or custom: the vendor sets the price, MarketNow verifies the security. No authentication required. Do NOT include secrets — the scanner rejects them.
  - after: Publish a skill to the MarketNow catalog (the write side). The package is validated and Sentinel-scanned (injection patterns, embedded secrets, dangerous APIs, suspicious URLs, typosquat, dedup against the 69k+ catalog) AND its claims are verified live: repo_url must exist (HTTP 200), install must reference a real package on npm/PyPI/crates/Docker Hub. False claims are rejected (422). Accepted skills with real substance (files/code/verifiable repo) are stored in the public auditable queue as certified-L1.5, pending L2 review and catalog merge. Description-only submissions are accepted but never merged. No authentication required. Do NOT include secrets — the scanner rejects them.
- 2026-10-10 `marketnow_fingerprint_tool` changed (title, annotations)
- 2026-10-10 `marketnow_check_revocation` changed (title, annotations)
- 2026-10-10 `marketnow_search_skills` changed (title, description, annotations) **meaning changed**
  - before: Search the MarketNow registry of 70k+ indexed MCP servers across 8 sources (npm, PyPI, GitHub, official-registry, Smithery, crates, Docker, curated), security-first scored, with live auth-gate state on official-registry endpoints — filter by auth openness (open/gated/late-gate/hard-gate) via /api/skills?auth=.
  - after: Search the MarketNow registry of indexed MCP servers (69k+ across GitHub, npm and PyPI, security-first scored).
- 2026-10-10 `marketnow_check_domain` changed (title, annotations)
- 2026-10-10 `marketnow_get_pipeline` changed (title, description, annotations)
  - before: Get the 12-stage credential-verification pipeline details (PARSE→DECISION).
  - after: Get the 12-stage verification pipeline details.
- 2026-10-10 `marketnow_list_formats` changed (title, description, annotations) **meaning changed**
  - before: List all 9 supported credential adapter formats (ATC, EAT-AI, ZTA, A2A, MCP Card, W3C VC, OAuth, SPIFFE, X.509) with their algorithms and status.
  - after: List all 8 supported credential formats with their algorithms and status.
- 2026-10-10 `marketnow_translate_credential` changed (title, description, annotations)
  - before: Translate a credential between the 9 adapter formats (ATC, JWT/OAuth, W3C VC, A2A, EAT-AI, ZTA, MCP Card, SPIFFE, X.509). Lossless conversion through Universal Trust Schema (UTS). See /api/trust?action=formats.
  - after: Translate a credential between 8 formats (ATC v3, JWT, W3C VC, A2A, EAT-AI, ZTA, MCP Card, X.509). Lossless conversion through Universal Trust Schema (UTS).
- 2026-10-10 `marketnow_verify_trust` changed (title, description, annotations)
  - before: Verify any AI agent credential (ATC v3, JWT/OAuth, W3C VC, MCP Card, A2A, EAT-AI, ZTA, SPIFFE SVID, X.509) through the UTA 12-stage credential-verification pipeline (PARSE→DECISION — distinct from Sentinel's 12 skill-audit stages). Returns validity, format, trust score, and issues.
  - after: Verify any AI agent credential (JWT, W3C VC, MCP Card, ATC v3, A2A, EAT-AI, ZTA, X.509) through the UTA 12-stage verification pipeline. Returns validity, format, trust score, and issues.
- 2026-10-05 `marketnow_submit_skill` changed (description)
  - before: Publish a skill to the MarketNow catalog (the write side). The package is validated and Sentinel-scanned (injection patterns, embedded secrets, dangerous APIs, suspicious URLs, typosquat, dedup against the 68k+ catalog) AND its claims are verified live: repo_url must exist (HTTP 200), install must reference a real package on npm/PyPI/crates/Docker Hub. False claims are rejected (422). Accepted skills with real substance (files/code/verifiable repo) are stored in the public auditable queue as certified-L1.5, pending L2 review and catalog merge. Description-only submissions are accepted but never merged. Any pricing model is accepted — free, per-call (x402), subscription or custom: the vendor sets the price, MarketNow verifies the security. No authentication required. Do NOT include secrets — the scanner rejects them.
  - after: Publish a skill to the MarketNow catalog (the write side). The package is validated and Sentinel-scanned (injection patterns, embedded secrets, dangerous APIs, suspicious URLs, typosquat, dedup against the 70k+ catalog) AND its claims are verified live: repo_url must exist (HTTP 200), install must reference a real package on npm/PyPI/crates/Docker Hub. False claims are rejected (422). Accepted skills with real substance (files/code/verifiable repo) are stored in the public auditable queue as certified-L1.5, pending L2 review and catalog merge. Description-only submissions are accepted but never merged. Any pricing model is accepted — free, per-call (x402), subscription or custom: the vendor sets the price, MarketNow verifies the security. No authentication required. Do NOT include secrets — the scanner rejects them.

Full history: https://api.protogrid.dev/v1/servers/io.github.alicelabs-llc%2Fmarketnow/changes

## Dependencies

- npm marketnow-mcp@1.15.0: resolved, 15 dependencies, MCP SDK @modelcontextprotocol/sdk 0.5.0
  - GHSA-w48q-cv73-mx4w (high) in `` @modelcontextprotocol/sdk@0.5.0 ``, direct, fixed in `` 1.24.0 ``, advisory summary: "Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default" https://osv.dev/vulnerability/GHSA-w48q-cv73-mx4w

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0.

## Remotes

- https://marketnow.site/api/mcp/ (streamable-http, auth none, reachable false, uptime30d 0.8333333)

## Packages

- npm marketnow-mcp@1.15.0

## Tools (9)

- `marketnow_check_domain`: Check if a domain is suspicious (scam checker). Returns risk score and reasons.
- `marketnow_check_revocation`: Check the revocation status of an Agent Trust Card (card_id) or CA key (kid) against the signed MarketNow Revocation Registry (MNR-CRL-1.0) + live ledger. Returns VALID/EXPIRED/REVOKED/SUPERSEDED/UNKNOWN with PERMIT/DENY recommendation. Fail-closed: unknown subjects answer UNKNOWN+DENY. The signed CRL layer is independently verifiable via Ed25519 (RFC 8785 JCS).
- `marketnow_fingerprint_tool`: Cryptographically fingerprint MCP tool definitions (OWASP MCP Cheat Sheet: 'verify tool descriptions haven't changed'). Computes RFC 8785 JCS + sha256 per tool plus a manifest fingerprint for the whole tools/list surface. Pass a previous manifest in 'pinned' to get a drift report (added/removed/changed) — the core defense against tool poisoning and rug-pull redefinitions.
- `marketnow_get_pipeline`: Get the 12-stage verification pipeline details.
- `marketnow_list_formats`: List all 8 supported credential formats with their algorithms and status.
- `marketnow_search_skills`: Search the MarketNow registry of indexed MCP servers (69k+ across GitHub, npm and PyPI, security-first scored).
- `marketnow_submit_skill`: Publish a skill to the MarketNow catalog (the write side). The package is validated and Sentinel-scanned (injection patterns, embedded secrets, dangerous APIs, suspicious URLs, typosquat, dedup against the 69k+ catalog) AND its claims are verified live: repo_url must exist (HTTP 200), install must reference a real package on npm/PyPI/crates/Docker Hub. False claims are rejected (422). Accepted skills with real substance (files/code/verifiable repo) are stored in the public auditable queue as certified-L1.5, pending L2 review and catalog merge. Description-only submissions are accepted but never merged. No authentication required. Do NOT include secrets — the scanner rejects them.
- `marketnow_translate_credential`: Translate a credential between 8 formats (ATC v3, JWT, W3C VC, A2A, EAT-AI, ZTA, MCP Card, X.509). Lossless conversion through Universal Trust Schema (UTS).
- `marketnow_verify_trust`: Verify any AI agent credential (JWT, W3C VC, MCP Card, ATC v3, A2A, EAT-AI, ZTA, X.509) through the UTA 12-stage verification pipeline. Returns validity, format, trust score, and issues.