Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.hoklims/stacksfinder

NPM · @STACKSFINDER/MCP-SERVER

Deterministic tech stack recommendations, audits, and project estimates. No hallucinations.

0 this week 78 Trust /100

Last scanned (22 hours ago)

Scores higher than 59% of npm servers

Category Developer Tools

Trust breakdown (7 categories)

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 Security81
  • No malware found by supply-chain analysis.Pass
  • CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available. View diagnostics → Fail
  • No install/post-install scripts declared.Pass
  • 31 of 93 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency47
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 295 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability71
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 2561 tokens (~111/item across 23 items; 23 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 Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety88
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 1 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "execute_mcp_installation" implies "execute" and declares readOnlyHint instead, contradicting what its own name says it does. See how to fix → Partial
  • An AI judge read all 23 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
What we tested

Checks we ran (16)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

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.

  • 19 Nov 26 +1
    • Stability: 0.97 → pass security
  • 18 Nov 26 −1
    • Stability: pass → 0.97 functional
  • 12 Nov 26 +1
    • Stability: 0.97 → pass security
  • 10 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Nov 26 −2
    • Stability: pass → 0.90 functional
  • 3 Nov 26 +1
    • Stability: 0.97 → pass security
  • 2 Nov 26 −1
    • Stability: pass → 0.97 functional
  • 27 Oct 26 +1
    • Stability: 0.97 → pass security
Diagnostics

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 21 Nov 2026 · Analysed npm/@stacksfinder/mcp-server@1.3.7

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Vulnerabilities 1 finding
ID CVE Severity Vector Fix available
GHSA-mrhx-c7xc-m3w5 CVE-2023-54404 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes

Background: What a vulnerability scan can and cannot prove →

Dependencies 93 packages
Packages resolved 93
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 23 exposed · ~2,561 tokens

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 →

Tool Tokens
analyze_repo_mcps ~191

Analyze your current repository to detect the tech stack and recommend relevant MCP servers. This tool examines your project files (package.json, .env, config files, etc.) to: 1. Detect frontend, backend, database, auth, hosting, and payment technologies 2. Find already installed MCP servers 3. Recommend new MCPs that would enhance your development workflow 4. Generate ready-to-use install configurations for Cursor, Claude Desktop, and Windsurf Example use cases: - "What MCPs would help with my project?" - "Analyze my repo and suggest useful MCP servers" - "Which MCPs am I missing based on my tech stack?"

NameTypeReqDescription
includeInstalledboolean–Include already installed MCPs (default: false)
mcpConfigPathstring–Override path to MCP configuration file
workspaceRootstring–Override workspace root directory (default: current directory)

No output schema declared.

No examples provided.

analyze_tech ~50

Detailed analysis of a technology with 6-dimension scores, strengths, weaknesses, and compatible technologies.

NameTypeReqDescription
contextstring–Context for scoring
technologystringyesTechnology ID to analyze

No output schema declared.

No examples provided.

check_mcp_compatibility ~270

Check compatibility between MCP servers. Detects conflicts (e.g., two database providers), redundancies (e.g., two ORMs), and synergies (e.g., GitHub + Vercel). Returns a health score (0-100) with grade (A/B/C/D) and detailed breakdown. **Examples:** - Check database compatibility: `["supabase-mcp", "neon-mcp"]` → conflict detected - Check ORM redundancy: `["prisma-mcp", "drizzle-mcp"]` → redundancy warning - Check synergies: `["stripe-mcp", "resend-mcp"]` → synergy detected **Supported MCP IDs include:** - supabase-mcp - neon-mcp - planetscale-mcp - turso-mcp - prisma-mcp - drizzle-mcp - clerk-mcp - auth0-mcp - stripe-mcp - paddle-mcp ...and more. **Aliases supported:** - "supabase" → "supabase-mcp" - "@neondatabase/mcp" → "neon-mcp" - "stripe" → "stripe-mcp"

NameTypeReqDescription
mcpsarrayyesArray of MCP server IDs to check compatibility between

No output schema declared.

No examples provided.

compare_audits ~74

Compare two audit reports to track technical debt trends over time. Shows new issues introduced, issues resolved, and health score change. Useful for measuring progress on debt reduction.

NameTypeReqDescription
baseAuditIdstringyesBase (older) audit ID
compareAuditIdstringyesCompare (newer) audit ID

No output schema declared.

No examples provided.

compare_techs ~49

Side-by-side comparison of 2-4 technologies with per-dimension winners and compatibility matrix.

NameTypeReqDescription
contextstring–Context for scoring
technologiesarrayyesTechnologies to compare

No output schema declared.

No examples provided.

create_audit ~88

Create a technical debt audit for a list of technologies. Analyzes your stack for deprecated packages, security vulnerabilities, EOL versions, and upgrade recommendations. Returns findings with severity (critical/high/medium/low/info) and actionable suggestions. Requires API key with audit:write scope.

NameTypeReqDescription
namestringyesName for the audit report
technologiesarrayyesTechnologies to audit

No output schema declared.

No examples provided.

create_blueprint ~207

Creates a new tech stack blueprint for a project. Requires API key with 'blueprint:write' scope. The blueprint generation is asynchronous. By default, this tool waits for completion and returns the full blueprint. Set waitForCompletion=false to get the job ID immediately for manual polling. Example usage: - Create a SaaS MVP: projectType="saas", scale="mvp", priorities=["time-to-market", "cost-efficiency"] - Create an enterprise API: projectType="api", scale="enterprise", priorities=["security", "scalability"]

NameTypeReqDescription
constraintsarray–Technology constraint IDs (optional)
prioritiesarray–Top 3 priorities (optional)
projectDescriptionstring–Brief description (optional)
projectNamestring–Project name (optional)
projectTypestringyesType of project
scalestringyesProject scale
waitForCompletionboolean–Wait for completion (default: true)

No output schema declared.

No examples provided.

estimate_project ~217

Estimate scope, pricing, and analyze market for a software project. Provides: - Detailed hour breakdown by feature (with complexity assessment) - Price ranges by team seniority level (junior/mid/senior/expert) - Competitor analysis and market trends (real-time via Perplexity) [Pro tier] - Market size and gaps identification [Pro tier] - Risk identification with mitigation suggestions Perfect for freelancers and agencies creating quotes. Requires API key with estimate:write scope. **Pricing is 100% deterministic** - same inputs always produce same outputs. Market analysis is best-effort and may vary with web data changes.

NameTypeReqDescription
includeMarketboolean–Include market analysis (default: true, Pro tier only)
regionstring–Region for pricing (default: france)
seniorityLevelstring–Average team seniority (default: mid)
specsstringyesProject specifications (min 100 chars, max 10,000)
teamSizenumber–Number of developers

No output schema declared.

No examples provided.

execute_mcp_installation ~302

Read a .env-mcp configuration file and generate installation commands for the MCPs. This tool: 1. Reads the .env-mcp file generated by prepare_mcp_installation 2. Validates that required environment variables are present 3. Generates installation commands for the target IDE/client 4. Returns post-installation instructions Prerequisites: - Run prepare_mcp_installation first to generate .env-mcp - Fill in the required API keys and credentials in .env-mcp - Set INSTALL_xxx=false for MCPs you want to skip Supported targets: - claude-code: Generates 'claude mcp add-json' commands - claude-desktop: Generates JSON config for claude_desktop_config.json - cursor: Generates JSON config for Cursor MCP settings - vscode: Generates JSON config for VS Code MCP extension - windsurf: Generates JSON config for Windsurf Output: - Individual commands/configs for each ready MCP - Aggregate command (for Claude Code) or config (for others) - List of MCPs missing required credentials - Post-installation instructions

NameTypeReqDescription
dryRunboolean–Only generate commands without marking ready to execute (default: false)
envMcpPathstring–Path to .env-mcp file (default: .env-mcp in current directory)
targetClientstring–Target IDE/client for installation (default: claude-code)

No output schema declared.

No examples provided.

generate_mcp_kit ~218

Generate a complete project kit with optimal tech stack and MCP recommendations based on your project description. Describe your project and get: 1. **Optimal Tech Stack**: Best technologies for each category (frontend, backend, database, auth, hosting, payments) 2. **MCP Recommendations**: AI-assistant tools tailored to your chosen technologies 3. **Install Configurations**: Ready-to-use configs for Claude Desktop, Cursor, and Windsurf Example prompts: - "I'm building a SaaS for project management with real-time collaboration" - "Building an MVP for a marketplace connecting freelancers with clients" - "Creating an e-commerce platform with Stripe payments and PostgreSQL"

NameTypeReqDescription
constraintsarray–Tech constraints (e.g., must-use-postgresql)
prioritiesarray–Top priorities (max 3)
projectDescriptionstringyesDescribe your project (50-5000 chars)
projectTypestring–Project type (if known)
scalestring–Project scale (if known)

No output schema declared.

No examples provided.

get_audit ~35

Fetch a completed audit report by ID. Returns all findings and health score.

NameTypeReqDescription
auditIdstringyesAudit report UUID

No output schema declared.

No examples provided.

get_audit_quota ~20

Check your remaining audit quota for this month.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_blueprint ~43

Fetches an existing blueprint by ID. Blueprints are generated via the StacksFinder web UI. Requires API key.

NameTypeReqDescription
blueprintIdstringyesBlueprint UUID

No output schema declared.

No examples provided.

get_estimate_quota ~22

Check your remaining estimate quota for this week and month.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_migration_recommendation ~88

Analyze an audit report for migration opportunities. Returns a detailed migration recommendation including: - Technologies that should be replaced - Recommended modern alternatives - Migration roadmap with phases - Risk assessment - Builder constraints to pre-fill for generating a migration blueprint Use this after create_audit to get actionable migration guidance.

NameTypeReqDescription
auditIdstringyesAudit report UUID to analyze for migration

No output schema declared.

No examples provided.

list_api_keys ~23

Lists your StacksFinder API keys. Requires a configured API key.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_audits ~47

List your audit reports with pagination. Shows name, status, health score, and creation date.

NameTypeReqDescription
limitnumber–Max results
offsetnumber–Pagination offset

No output schema declared.

No examples provided.

list_technologies ~38

Lists all available technology IDs for use with other tools. Essential for discovering valid technology identifiers.

NameTypeReqDescription
categorystring–Filter by category

No output schema declared.

No examples provided.

prepare_mcp_installation ~303

Analyze your repository and generate a .env-mcp configuration file for MCP server installation. This tool: 1. Detects your tech stack from project files (package.json, .env, etc.) 2. Identifies which MCP servers would benefit your project 3. Finds already installed MCPs to avoid duplicates 4. Generates a .env-mcp template file with all required environment variables The generated .env-mcp file contains: - INSTALL_xxx flags to control which MCPs to install - Required and optional environment variables for each MCP - Documentation links and examples After running this tool: 1. Open the generated .env-mcp file 2. Fill in the API keys and configuration values 3. Set INSTALL_xxx=false for MCPs you don't want 4. Run execute_mcp_installation to complete the setup Example use cases: - "Prepare MCP installation for my project" - "Generate .env-mcp for my tech stack" - "What MCPs do I need and what credentials do they require?"

NameTypeReqDescription
envMcpPathstring–Path where .env-mcp will be created (default: .env-mcp in workspaceRoot)
includeInstalledboolean–Include already installed MCPs in the preparation (default: false)
mcpConfigPathstring–Override path to existing MCP configuration file
workspaceRootstring–Workspace root directory (default: current directory)

No output schema declared.

No examples provided.

recommend_stack ~72

Recommends the best tech stack for a project using real-time scoring with context adjustments. Requires API key.

NameTypeReqDescription
constraintsarray–Project constraints
prioritiesarray–Top priorities (max 3)
projectTypestringyesType of project
scalestring–Project scale

No output schema declared.

No examples provided.

recommend_stack_demo ~86

Try StacksFinder's tech stack recommendations for FREE - once per day, no account required. Returns the optimal technology for each category based on deterministic scoring. For unlimited access, priorities, constraints, and AI-generated narratives, upgrade to Pro at https://stacksfinder.com/pricing

NameTypeReqDescription
projectTypestringyesType of project
scalestring–Project scale

No output schema declared.

No examples provided.

revoke_api_key ~37

Revokes an API key. This action cannot be undone.

NameTypeReqDescription
keyIdstringyesThe UUID of the API key to revoke

No output schema declared.

No examples provided.

setup_api_key ~81

Authenticates with your StacksFinder account and creates an API key. Requires Pro or Team tier. The key is returned once and should be saved securely.

NameTypeReqDescription
emailstringyesYour StacksFinder account email
keyNamestring–Optional name for the API key
passwordstringyesYour StacksFinder account password

No output schema declared.

No examples provided.

Install

How do I install the io.github.hoklims/stacksfinder MCP server?

io.github.hoklims/stacksfinder runs locally as an npm package, launched with npx -y @stacksfinder/mcp-server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @stacksfinder/mcp-server

# add to Claude Code
claude mcp add hoklims-stacksfinder -- npx -y @stacksfinder/mcp-server
Common questions

What is the io.github.hoklims/stacksfinder MCP server?

io.github.hoklims/stacksfinder is an MCP server listed in the public MCP registry as io.github.hoklims/stacksfinder. Deterministic tech stack recommendations, audits, and project estimates. No hallucinations. This page covers its npm package (@stacksfinder/mcp-server).

Is the io.github.hoklims/stacksfinder MCP server safe to use?

io.github.hoklims/stacksfinder scores 78 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 21 November 2026. It declares no install or post-install scripts. 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 io.github.hoklims/stacksfinder MCP server expose?

io.github.hoklims/stacksfinder exposes 23 tools: list_technologies, analyze_tech, compare_techs, recommend_stack_demo, recommend_stack, and 18 more. Their descriptions and schemas cost roughly 2,561 tokens of context every time the server is loaded.

Is the io.github.hoklims/stacksfinder MCP server still maintained?

io.github.hoklims/stacksfinder is still listed as active in the MCP registry. We last reached this channel on 21 November 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 io.github.hoklims/stacksfinder MCP server under?

io.github.hoklims/stacksfinder declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the io.github.hoklims/stacksfinder MCP server?

VerifyMCP ran 16 checks on io.github.hoklims/stacksfinder, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.