protogrid

Search / io.github.jdhart81/security-preflight

security-preflight

R0· no sign-in

Static MCP, source-code and injection-indicator checks with redacted signed receipts.

v1.3.1 · active · repository · descriptor JSON · versions

An agent can connect right now, no human step.Remote endpoint, no authentication, reachable on the last probe.
Quality75good
Trust83of 100
Uptime, 30 days100%
Latency p50248 ms

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "security-preflight": {
      "type": "http",
      "url": "https://mcp.viridis-security.com/security-preflight/mcp"
    }
  }
}
claude mcp add --transport http security-preflight https://mcp.viridis-security.com/security-preflight/mcp
[mcp_servers.security-preflight]
url = "https://mcp.viridis-security.com/security-preflight/mcp"
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "security-preflight": {
      "type": "remote",
      "url": "https://mcp.viridis-security.com/security-preflight/mcp",
      "enabled": true
    }
  }
}
{
  "mcpServers": {
    "security-preflight": {
      "type": "http",
      "url": "https://mcp.viridis-security.com/security-preflight/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=security-preflight&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vbWNwLnZpcmlkaXMtc2VjdXJpdHkuY29tL3NlY3VyaXR5LXByZWZsaWdodC9tY3AifQ%3D%3D"
}
{
  "servers": {
    "security-preflight": {
      "type": "http",
      "url": "https://mcp.viridis-security.com/security-preflight/mcp"
    }
  }
}
{
  "mcpServers": {
    "security-preflight": {
      "httpUrl": "https://mcp.viridis-security.com/security-preflight/mcp"
    }
  }
}
extensions:
  "security-preflight":
    enabled: true
    name: "security-preflight"
    type: streamable_http
    uri: "https://mcp.viridis-security.com/security-preflight/mcp"
    timeout: 300

Quality 75 / 100good

protocol75 · weight 25
  • warn
    protocol.modernnewest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
  • n/a
    protocol.statelessonly applies to 2026-07-28 servers
  • pass
    protocol.transportstreamable HTTP
  • n/a
    protocol.list_ttlonly applies to 2026-07-28 servers
authorizationn/a · weight 15
  • n/a
    auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
  • n/a
    auth.secret_in_urlno templated URL
tool hygiene100 · weight 30
  • pass
    tools.descriptionsevery tool has a description
  • pass
    tools.description_lengthdescriptions are concise
  • pass
    tools.schemasevery tool has an object input schema
  • pass
    tools.annotations5 of 5 tools declare readOnlyHint or destructiveHint
  • pass
    tools.directory_hintsevery tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
  • pass
    tools.token_costabout 837 tokens to load every tool
  • pass
    tools.api_dumptools are not a one-to-one API dump
stability25 · weight 15
  • warn
    stability.changes10 tool changes in 30 days
  • fail
    stability.rug_pull1 tools kept their name but changed most of their description in 30 days; review before trusting them
dependenciesn/a · weight 15
  • n/a
    deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

5 tools, about 837 tokens to load them all · tool set 8c34849191b0 · tools last changed 2026-10-07 · checked 2026-10-19 10:20 UTC

Tool changes

  • describe_agentchangedtitle
  • get_security_receiptchangedtitle
  • screen_injectionchangedtitle
  • scan_sourcechangedtitle
  • security_preflightchangedtitle
  • describe_agentchangedannotations
  • get_security_receiptchangeddescription, annotationsmeaning changed
    before

    Read a previously issued public, input-redacted receipt.

    after · 11% of words in common

    Read an unsigned, filtered public view; retain original delivery for signature verification.

  • screen_injectionchangeddescription, input schema, annotations
    before

    $1 batch of 1–20 text samples screened for deterministic injection markers. Maximum 64 KiB total. Heuristic indicators, not calibrated probabilities or a guarantee of safety. No model calls or automatic follow-on purchase.

    after · 74% of words in common

    $1 batch of 1–20 text samples screened for deterministic injection markers. Direct MCP requires the checkout caller and verified fixed-order session. Maximum 64 KiB total. Heuristic indicators, not calibrated probabilities or a guarantee of safety. No model calls or automatic follow-on purchase.

  • scan_sourcechangeddescription, input schema, annotations
    before

    $1 bounded inline VulnCanon source scan; indicators, not proven exploits. At most 64 KiB, 2000 lines, 4096 characters per line. No model calls, repository fetching or code execution. Returns a redacted signed receipt.

    after · 75% of words in common

    $1 bounded inline VulnCanon source scan; indicators, not proven exploits. Direct MCP requires the checkout caller and verified fixed-order session. At most 64 KiB, 2000 lines, 4096 characters per line. No model calls, repository fetching or code execution. Returns a redacted signed receipt.

  • security_preflightchangeddescription, input schema, annotations
    before

    Run a $1 static Security Preflight and return a signed receipt. New x402 payer wallets may receive the fleet-wide $0.01 introductory call. No deployed endpoint is fetched or tested. Importing the receipt into an Agent Market profile is a separate, explicit action.

    after · 53% of words in common

    Run a $1 static Security Preflight and return a signed receipt. Direct MCP requires the checkout caller and verified fixed-order session. The separate x402 HTTP rail retains its existing introductory quote policy. No deployed endpoint is fetched or tested. Importing the receipt into an Agent Market profile is a separate, explicit action.

Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 83 / 100

duplicate-repo
provenance80
liveness100
freshness85
hygiene60

+repository +namespace-matches-repo +reachable +uptime-100% ~updated-31d-ago -duplicate-repo(32 names)

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remoteauthreachableuptime 30dp50protocollast ok
https://mcp.viridis-security.com/security-preflight/mcp streamable-httpnoneyes100%248 ms2025-11-252026-10-19

Tools (5)

describe_agentread-onlyDescribe scope, evidence boundary, inputs, and outputs.
get_security_receiptread-onlyRead an unsigned, filtered public view; retain original delivery for signature verification.
scan_source$1 bounded inline VulnCanon source scan; indicators, not proven exploits. Direct MCP requires the checkout caller and verified fixed-order session. At most 64 KiB, 2000 lines, 4096 characters per line. No model calls, repository fetching or code execution. Returns a redacted signed receipt.
screen_injection$1 batch of 1–20 text samples screened for deterministic injection markers. Direct MCP requires the checkout caller and verified fixed-order session. Maximum 64 KiB total. Heuristic indicators, not calibrated probabilities or a guarantee of safety. No model calls or automatic follow-on purchase.
security_preflightRun a $1 static Security Preflight and return a signed receipt. Direct MCP requires the checkout caller and verified fixed-order session. The separate x402 HTTP rail retains its existing introductory quote policy. No deployed endpoint is fetched or tested. Importing the receipt into an Agent Market profile is a separate, explicit action.

Schemas: list_tools.

Also listed as

31 other active names share this repository (showing 10): io.github.jdhart81/agent-arbitration, io.github.jdhart81/agent-compute-ledger, io.github.jdhart81/agent-covenant, io.github.jdhart81/agent-erc8004-bridge, io.github.jdhart81/agent-escrow, io.github.jdhart81/agent-hive-orchestrator, io.github.jdhart81/agent-identity-registry, io.github.jdhart81/agent-market-network, io.github.jdhart81/agent-metering, io.github.jdhart81/agent-notary

Similar MCP servers

More from io.github.jdhart81

And 26 more from this publisher.

Official server.json
{
  "name": "io.github.jdhart81/security-preflight",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://mcp.viridis-security.com/security-preflight/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "1.3.1",
  "repository": {
    "url": "https://github.com/jdhart81/viridis-agent-fleet",
    "source": "github"
  },
  "description": "Static MCP, source-code and injection-indicator checks with redacted signed receipts."
}