registry / rally-project-brain-mcp / 0.1.5

rally-project-brain-mcp@0.1.5

MCP server exposing Rally Project Brain to any MCP-compatible agent (Claude Code, Cursor, Copilot agent mode, Windsurf, ...)

AI Security Review

scanned 6d ago · by lpm-firewall-ai

The source ties the configuration writes to an explicit login flow that prompts for a Rally token, and the package manifest has no lifecycle hooks. The agent configuration and instruction-file changes support the package’s stated onboarding function, with no confirmed attack behavior.

Static reason

No blocking static signals were detected.

Trigger

A user invokes the login command and provides an agent token.

Impact

The configured agent can access Rally project tools; the inspected behavior does not establish unconsented agent control-surface mutation or credential theft.

Mechanism

The flow verifies the token with the Rally backend, adds a Rally MCP server entry to supported configuration files, and adds an onboarding note to project instruction files.

AI rationale

Evidence

package.jsonindex.mjs

Network endpoints1

rally-backend.fly.dev

Decision evidence

public snapshot

AI called this Clean at 91.0% confidence as Benign with low false-positive risk.

Evidence for AI clean decision

The package exposes index.mjs as its CLI entrypoint and declares no lifecycle scripts.
Configuration writes are reached through the explicit login command, which prompts for a Rally agent token.
Login uses the token to verify the account with the configured Rally backend, then adds the MCP server to project and agent configuration files.
The onboarding flow adds a Rally instruction note to supported project instruction files.

Evidence against

Behavioral surface

Source

EnvironmentVarsFilesystemNetwork

Supply chain

HighEntropyStringsUrlStrings

Manifest

NoLicense

scanned 2 file(s), 24.8 KB of source, external domains: rally-backend.fly.dev

Source & flagged code

6 flagged

index.mjsView file

•Manifest-trigger-reachable source links an external AI-agent control path to a behavior-bearing write operation. const clinebase = process.platform === "win32" ? path.join(process.env.appdata || path.join(os.homedir(), "appdata", "roaming"), "code", "user", "globalstorage") : process.platform === "darwin" ? path.join(os.homedir(), "library", "application support", "code", "user", "globalstorage") : path.join(os.homedir(), ".config", "code", "user", "globalstorage"); const clinepath = path.join(clinebase, "saoudrizwan.claude-dev", "settings", "cline_mcp_settings.json"); try { const clineextensiondir = path.join(clinebase, "saoudrizwan.claude-dev"); const clineinstalled = await stat(clineextensiondir).then(() => true).catch(() => false); if (cl

High

Trigger Reachable External Ai Agent Control Surface Mutation

Manifest-trigger-reachable source writes behavior-bearing configuration into a user or project AI-agent control surface.

index.mjsView on unpkg

76".mcp.json"); // Reference it as `npx rally-project-brain-mcp`, not a resolved absolute // path — now that the package is actually published, this is strictly // better: t

Low

Ai Review Evidence

Login uses the token to verify the account with the configured Rally backend, then adds the MCP server to project and agent configuration files.

index.mjsView on unpkg · L76

320if (process.argv[2] === "login") { await runLoginAgent(); process.exit(process.exitCode ?? 0); } const BASE_URL = process.env.RALLY_BACKEND_URL || "http://localhost:8080"; con

Low

Ai Review Evidence

Configuration writes are reached through the explicit login command, which prompts for a Rally agent token.

index.mjsView on unpkg · L320

51async function runLoginAgent() { const backendUrl = process.env.RALLY_BACKEND_URL || "https://rally-backend.fly.dev"; const rl = createInterface({ input: process.stdin, output: process.stdout });

Low

Ai Review Evidence

Login uses the token to verify the account with the configured Rally backend, then adds the MCP server to project and agent configuration files.

index.mjsView on unpkg · L51

index.mjs#virtual:normalized:round1View file

•stage = ast_semantic_analysis; reason = ast_parse_error; limitedFiles = 1

High

Semantic Analysis Limited

A bounded semantic-analysis stage reached its safety limit; remaining detectors completed, but this package requires AI review.

index.mjs#virtual:normalized:round1View on unpkg

package.jsonView file

1{ "name": "rally-project-brain-mcp", "version": "0.1.5", "description": "MCP server exposing Rally Project Brain to any MCP-compatible agent (Claude Code, Cursor, Copilot agent mode, Windsurf, ...)", "main": "index.mjs", "type": "module", "license": "UNLICENSED", "repository": { "type": "git", "url": "git+https://github.com/neeldevsen/Rally_Backend.git", "directory": "mcp-server" }, "engines": { "node": ">=18" }, "bin": { "rally-project-brain-mcp": "index.mjs" }, "dependencies": { "@modelcontextprotocol/sdk": "^1.30.0", "smol-toml": "^1.8.0

Low

Suspicious Lifecycle Evidence

The package exposes index.mjs as its CLI entrypoint and declares no lifecycle scripts.

package.jsonView on unpkg · L1

Source & flagged code

6 flagged · loading source

index.mjsView file

High

Trigger Reachable External Ai Agent Control Surface Mutation

Manifest-trigger-reachable source writes behavior-bearing configuration into a user or project AI-agent control surface.

index.mjsView on unpkg

76".mcp.json"); // Reference it as `npx rally-project-brain-mcp`, not a resolved absolute // path — now that the package is actually published, this is strictly // better: t

Low

Ai Review Evidence

Login uses the token to verify the account with the configured Rally backend, then adds the MCP server to project and agent configuration files.

index.mjsView on unpkg · L76

Findings

2 High2 Medium8 Low

HighTrigger Reachable External Ai Agent Control Surface Mutationindex.mjs

HighSemantic Analysis Limitedindex.mjs#virtual:normalized:round1

MediumNetwork

MediumEnvironment Vars

LowFilesystem

LowHigh Entropy Strings

LowUrl Strings

LowNo License

LowSuspicious Lifecycle Evidencepackage.json

LowAi Review Evidenceindex.mjs

Affected versions and remediation

This report applies to rally-project-brain-mcp@0.1.5.

See all versions of rally-project-brain-mcp for other recorded verdicts.

Review the evidence and your use of rally-project-brain-mcp@0.1.5 before allowing it. Restrict the permissions described in this report.
Choose an independently verified alternative or release. This report does not establish that other versions are safe.

Evidence last updated: 2026-10-17 04:22:25.467Z (UTC).

Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.