Skip to content

BRAINIAC Application & Pipeline Security Checks MCP server

software.brainiac/appsec-configbrainiac.softwarestreamable-httpv1.0.1Scanned

Paid Application & Pipeline Security Checks API via x402. Unpaid tool calls return 402.

15 tools: 8 change things and 7 only read.

Tools: 0 delete, 0 irreversible, 8 write, 7 read.
  • Reads private data · 4
  • Reads text others write · 15
  • Can send data out · 0
  • 2 findings

Tools listed without sign-in. Remote posture

With Anlyon

8 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the BRAINIAC Application & Pipeline Security Checks MCP server can do

The BRAINIAC Application & Pipeline Security Checks MCP server is published by brainiac.software, a domain the MCP Registry verified. It has 15 tools. It can create or change data (8 tools: appsec-config_gitlab-ci-audit, appsec-config_cloudformation-audit, appsec-config_regex-redos-check, appsec-config_injection-sink-scan and 4 more), but cannot delete data. 7 tools only read.

4 tools read private data (appsec-config_secrets-scan, appsec-config_github-actions-audit, appsec-config_jwt-inspect and 1 more); 15 tools bring in text other people can write (appsec-config_secrets-scan, appsec-config_github-actions-audit, appsec-config_gitlab-ci-audit and 12 more).

The fixed checks matched 2 findings (annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 20, 2026, version 1.0.1.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

15 tools

Changes things 8Claude Code: ask
  • appsec-config_cloudformation-auditFlag public storage, open security groups, missing encryption and wildcard IAM.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Flag public storage, open security groups, missing encryption and wildcard IAM. Price $0.04 USDC. POST /api/v1/appsec-config/cloudformation-audit. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Audit CloudFormation templates
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • appsec-config_gitlab-ci-auditFlag unpinned images, remote includes, secrets and dind risks.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Flag unpinned images, remote includes, secrets and dind risks. Price $0.03 USDC. POST /api/v1/appsec-config/gitlab-ci-audit. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Audit GitLab CI configuration
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • appsec-config_injection-sink-scanLightweight single-file taint scan for SQL, command and XSS sinks.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Lightweight single-file taint scan for SQL, command and XSS sinks. Price $0.03 USDC. POST /api/v1/appsec-config/injection-sink-scan. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Scan a file for injection sinks
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • appsec-config_oauth-client-auditCheck client settings against RFC 9700 security BCP.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Check client settings against RFC 9700 security BCP. Price $0.02 USDC. POST /api/v1/appsec-config/oauth-client-audit. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Audit OAuth/OIDC client registration
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • appsec-config_openapi-security-auditOWASP API Top 10 style checks on an OpenAPI document.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    OWASP API Top 10 style checks on an OpenAPI document. Price $0.04 USDC. POST /api/v1/appsec-config/openapi-security-audit. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Audit OpenAPI 3.x security design
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • appsec-config_password-policy-evaluateCheck policy fields and optional samples against NIST SP 800-63B-4.Reads text others write1 finding

    Why it is in this group

    • The name "appsec-config_password-policy-evaluate" says "evaluate": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Warn

      The server marks "appsec-config_password-policy-evaluate" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "appsec-config_password-policy-evaluate" says "evaluate": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Check policy fields and optional samples against NIST SP 800-63B-4. Price $0.02 USDC. POST /api/v1/appsec-config/password-policy-evaluate. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Evaluate a password policy vs NIST
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • appsec-config_regex-redos-checkCheck a JavaScript regex for catastrophic backtracking with recheck.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Check a JavaScript regex for catastrophic backtracking with recheck. Price $0.02 USDC. POST /api/v1/appsec-config/regex-redos-check. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Detect ReDoS risk in a regular expression
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • appsec-config_sbom-generateBuild CycloneDX or SPDX SBOMs from npm/PyPI/Go/Cargo lockfiles.Reads text others write1 finding

    Why it is in this group

    • The name "appsec-config_sbom-generate" says "generate": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Warn

      The server marks "appsec-config_sbom-generate" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "appsec-config_sbom-generate" says "generate": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Build CycloneDX or SPDX SBOMs from npm/PyPI/Go/Cargo lockfiles. Price $0.03 USDC. POST /api/v1/appsec-config/sbom-generate. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Generate an SBOM from a lockfile
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Only reads 7Show 7 read-only tools
  • appsec-config_apache-config-auditFind weak TLS, directory listing, TRACE and missing hardening.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The description's first verb is "find": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "find" and "directory": it reads files.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Find weak TLS, directory listing, TRACE and missing hardening. Price $0.03 USDC. POST /api/v1/appsec-config/apache-config-audit. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Audit Apache httpd configuration
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • appsec-config_aws-iam-policy-analyzeFind wildcards, NotAction pitfalls, privilege-escalation actions and public principals.Reads text others writeNo findings

    Why it is in this group

    • The name "appsec-config_aws-iam-policy-analyze" says "analyze": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Find wildcards, NotAction pitfalls, privilege-escalation actions and public principals. Price $0.03 USDC. POST /api/v1/appsec-config/aws-iam-policy-analyze. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Analyse AWS IAM policy documents
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • appsec-config_gcp-iam-binding-analyzeFlag basic roles, public members and service-account impersonation.Reads text others writeNo findings

    Why it is in this group

    • The name "appsec-config_gcp-iam-binding-analyze" says "analyze": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Flag basic roles, public members and service-account impersonation. Price $0.03 USDC. POST /api/v1/appsec-config/gcp-iam-binding-analyze. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Analyse GCP IAM policy bindings
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • appsec-config_github-actions-auditFind injection, pinning, permission and pull_request_target risks.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The description's first verb is "find": a word for reading.

    What it can reach

    • private-dataThe input names a file (input.files), and the tool reads: it reads files.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe description's first sentence says "find" and "pull request": it reads issues, which other people can write.
    Description, as the server wrote it
    Find injection, pinning, permission and pull_request_target risks. Price $0.03 USDC. POST /api/v1/appsec-config/github-actions-audit. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Audit GitHub Actions workflows
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • appsec-config_jwt-inspectDecode JWTs, flag alg:none, weak HMAC secrets and lifetime issues.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "appsec-config_jwt-inspect" says "inspect": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "secret": it reads secrets.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe description's first sentence says "issue": it reads issues, which other people can write.
    Description, as the server wrote it
    Decode JWTs, flag alg:none, weak HMAC secrets and lifetime issues. Price $0.03 USDC. POST /api/v1/appsec-config/jwt-inspect. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Inspect JWTs for weak crypto and claims
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • appsec-config_nginx-config-auditFind weak TLS, alias traversal, open proxy and missing headers.Reads text others writeNo findings

    Why it is in this group

    • The description's first verb is "find": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Find weak TLS, alias traversal, open proxy and missing headers. Price $0.03 USDC. POST /api/v1/appsec-config/nginx-config-audit. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Audit nginx configuration
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • appsec-config_secrets-scanFind secrets in text or diffs using vendored gitleaks rules with redaction.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The description's first verb is "find": a word for reading.

    What it can reach

    • private-dataThe name "appsec-config_secrets-scan" says "secret": it reads secrets.
    • private-dataThe description's first sentence says "find" and "secret": it reads secrets.
    • private-dataThe input names a file (input.files), and the tool reads: it reads files.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Find secrets in text or diffs using vendored gitleaks rules with redaction. Price $0.04 USDC. POST /api/v1/appsec-config/secrets-scan. An unpaid call returns the x402 payment terms and does not run.

    Annotations the server declares

    • title: Scan files for secrets with gitleaks rules
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.

Reads private data4
Reads files, mail, messages, databases, secrets, calendars or repositories.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:26 UTC, unchanged since Nov 20, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
8
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 8 tools that change things (8 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://www.brainiac.software/mcp/appsec-config: tools/list returned 15 tools to an anonymous client, including appsec-config_gitlab-ci-audit (write), appsec-config_cloudformation-audit (write), appsec-config_regex-redos-check (write), appsec-config_injection-sink-scan (write), appsec-config_openapi-security-audit (write) and 3 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

2 warn
  • The server marks "appsec-config_password-policy-evaluate" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "appsec-config_password-policy-evaluate" says "evaluate": a word for a change.

    What this check looks for
  • The server marks "appsec-config_sbom-generate" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "appsec-config_sbom-generate" says "generate": a word for a change.

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools15 changed.~15 changedView diff

Install

Pinned to version 1.0.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http appsec-config https://www.brainiac.software/mcp/appsec-config
claude mcp add --transport http appsec-config https://www.brainiac.software/mcp/appsec-config

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__appsec-config__appsec-config_secrets-scan",
      "mcp__appsec-config__appsec-config_github-actions-audit",
      "mcp__appsec-config__appsec-config_aws-iam-policy-analyze",
      "mcp__appsec-config__appsec-config_gcp-iam-binding-analyze",
      "mcp__appsec-config__appsec-config_jwt-inspect",
      "mcp__appsec-config__appsec-config_nginx-config-audit",
      "mcp__appsec-config__appsec-config_apache-config-audit"
    ],
    "ask": [
      "mcp__appsec-config__appsec-config_gitlab-ci-audit",
      "mcp__appsec-config__appsec-config_cloudformation-audit",
      "mcp__appsec-config__appsec-config_regex-redos-check",
      "mcp__appsec-config__appsec-config_injection-sink-scan",
      "mcp__appsec-config__appsec-config_openapi-security-audit",
      "mcp__appsec-config__appsec-config_password-policy-evaluate",
      "mcp__appsec-config__appsec-config_sbom-generate",
      "mcp__appsec-config__appsec-config_oauth-client-audit"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as appsec-config. Review it before you use it.

Capability tags behind 15 rules
  • mcp__appsec-config__appsec-config_secrets-scan private-data, untrusted-input
  • mcp__appsec-config__appsec-config_github-actions-audit private-data, untrusted-input
  • mcp__appsec-config__appsec-config_gitlab-ci-audit untrusted-input
  • mcp__appsec-config__appsec-config_cloudformation-audit untrusted-input
  • mcp__appsec-config__appsec-config_aws-iam-policy-analyze untrusted-input
  • mcp__appsec-config__appsec-config_gcp-iam-binding-analyze untrusted-input
  • mcp__appsec-config__appsec-config_jwt-inspect private-data, untrusted-input
  • mcp__appsec-config__appsec-config_regex-redos-check untrusted-input
  • mcp__appsec-config__appsec-config_injection-sink-scan untrusted-input
  • mcp__appsec-config__appsec-config_openapi-security-audit untrusted-input
  • mcp__appsec-config__appsec-config_password-policy-evaluate untrusted-input
  • mcp__appsec-config__appsec-config_sbom-generate untrusted-input
  • mcp__appsec-config__appsec-config_nginx-config-audit untrusted-input
  • mcp__appsec-config__appsec-config_apache-config-audit private-data, untrusted-input
  • mcp__appsec-config__appsec-config_oauth-client-audit untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/software.brainiac/appsec-config/verify?hash=7ef6c107cebef345498987867ad0d05de18e5053d58775a10c858bf54022ff7e" | jq -e '.changed == false'

Pinned hash 7ef6c107cebe, from Nov 20, 2026, 01:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/software.brainiac/appsec-config/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for software.brainiac/appsec-config
[![Anlyon Radar](https://radar.anlyon.com/badge/software.brainiac/appsec-config.svg)](https://radar.anlyon.com/servers/software.brainiac/appsec-config)

Source: MCP Registry. Synced Nov 20, 2026, 01:17 UTC.

BRAINIAC Application & Pipeline Security Checks MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the BRAINIAC Application & Pipeline Security Checks MCP server safe?

No scan can promise that. What its definitions show: 15 tools, 8 of which can change, send or delete something, and 2 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the BRAINIAC Application & Pipeline Security Checks MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the BRAINIAC Application & Pipeline Security Checks MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the BRAINIAC Application & Pipeline Security Checks MCP server have?

15 tools: 8 write, 7 read. appsec-config_gitlab-ci-audit, appsec-config_cloudformation-audit, appsec-config_regex-redos-check, appsec-config_injection-sink-scan, appsec-config_openapi-security-audit, appsec-config_password-policy-evaluate, appsec-config_sbom-generate, appsec-config_oauth-client-audit and 7 more.

Does the BRAINIAC Application & Pipeline Security Checks MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the BRAINIAC Application & Pipeline Security Checks MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the BRAINIAC Application & Pipeline Security Checks MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 20, 2026. Every change is on this page and in its Atom feed.