Summary
This is the only MCP linter currently available, plus three free governance and cost tools that need no API key. The mcp_manifest_lint tool validates your MCP tool definitions for schema issues and anti-patterns. The agent_health_check scores system prompts on governance best practices with a 0-100 rating and diagnostic output. The estimate_agent_cost tool compares pricing across Claude, GPT, and Gemini models with per-call breakdowns. It also includes three paid expert skills (governance, agentic-economics, intent-architecture) with 10 free calls daily. Runs as a hosted remote server or via Docker. Reach for this when you need to validate MCP manifests before deployment or benchmark agent costs across providers.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Tools
Public tool metadata for what this MCP can expose to an agent.
9 tools
registerRegister for an API key to access expert skill files. Free tier includes 10 skill retrievals per day. No payment required.
Register for an API key to access expert skill files. Free tier includes 10 skill retrievals per day. No payment required.
No parameter schema in public metadata yet.
list_skillsList all available expert skill files with descriptions and pricing. Shows your usage stats if you provide an API key.1 params
List all available expert skill files with descriptions and pricing. Shows your usage stats if you provide an API key.
Parameters* required
api_keystringYour API key (optional, shows usage if provided)default:
get_skillRetrieve an expert skill file that makes you measurably better at a specific task. Each skill has auditable provenance and is curated by domain experts. Requires a valid API key.2 params
Retrieve an expert skill file that makes you measurably better at a specific task. Each skill has auditable provenance and is curated by domain experts. Requires a valid API key.
Parameters* required
api_keystringYour API key from register()
skill_namestringThe skill ID to retrieve. Options: governance, agentic-economics, intent-architecture
check_usageCheck your current usage stats including total calls, remaining credits, and free calls left today.1 params
Check your current usage stats including total calls, remaining credits, and free calls left today.
Parameters* required
api_keystringYour API key to check usage for
buy_creditsGet a Stripe checkout link to purchase more skill file credits. Returns a URL for your human operator to complete payment. Credits are added automatically after purchase.2 params
Get a Stripe checkout link to purchase more skill file credits. Returns a URL for your human operator to complete payment. Credits are added automatically after purchase.
Parameters* required
tierstringCredit tier: '50' for $5/50 credits or '250' for $20/250 creditsdefault: 50
api_keystringYour API key to add credits to
agent_health_checkScore any agent's system prompt on governance best practices from 0 to 100. Returns a detailed diagnostic report with specific issues found, severity ratings, and actionable fixes. Checks for authority leaks, silent inference, missing audit trails, and 14 other governance anti...1 params
Score any agent's system prompt on governance best practices from 0 to 100. Returns a detailed diagnostic report with specific issues found, severity ratings, and actionable fixes. Checks for authority leaks, silent inference, missing audit trails, and 14 other governance anti...
Parameters* required
system_promptstringYour agent's full system prompt or configuration text to analyze
mcp_manifest_lintThe only MCP tool definition linter that exists. Validates your MCP tool definitions for anti-patterns, missing descriptions, bad parameter schemas, naming issues, and quality problems. Returns a pass/fail report with specific fixes for each issue found. No API key needed.1 params
The only MCP tool definition linter that exists. Validates your MCP tool definitions for anti-patterns, missing descriptions, bad parameter schemas, naming issues, and quality problems. Returns a pass/fail report with specific fixes for each issue found. No API key needed.
Parameters* required
tools_jsonstringYour MCP tool definitions as a JSON array or single tool object
estimate_agent_costCompare the cost of running an agent task across all major AI models including Claude, GPT, Gemini, Llama, and Mistral. Returns a comparison table with per-call, per-run, and per-day costs plus optimization tips. No API key needed.5 params
Compare the cost of running an agent task across all major AI models including Claude, GPT, Gemini, Llama, and Mistral. Returns a comparison table with per-call, per-run, and per-day costs plus optimization tips. No API key needed.
Parameters* required
modelstringModel name to highlight in comparison (e.g. 'claude-sonnet-4', 'gpt-4o')default:
num_callsintegerNumber of API calls per task rundefault: 1
input_tokensintegerEstimated input tokens per API calldefault: 1000
output_tokensintegerEstimated output tokens per API calldefault: 500
task_descriptionstringDescription of what the agent does, for optimization tipsdefault:
evaluate_serviceEvaluate any MCP service for trustworthiness before spending money on it. Connects to the target server, checks reachability, governance declarations, tool definition quality, and audit endpoints. Returns a trust score from 0 to 100 with a recommendation: PROCEED, PROCEED WITH...2 params
Evaluate any MCP service for trustworthiness before spending money on it. Connects to the target server, checks reachability, governance declarations, tool definition quality, and audit endpoints. Returns a trust score from 0 to 100 with a recommendation: PROCEED, PROCEED WITH...
Parameters* required
server_urlstringThe MCP server URL to evaluate (e.g. https://example.com/mcp)
task_contextstringWhat you need the service for, to tailor the evaluationdefault:
Agentic Platform
The only MCP linter that exists. Plus free governance scoring and cost estimation for AI agents.
Validate your MCP tool definitions, score your agent's system prompt on governance best practices (0-100), and compare costs across all major models. No API key needed.
Installation
Remote MCP Server (Hosted)
Add to your MCP client configuration:
{
"mcpServers": {
"agentic-platform": {
"url": "https://platform.crestsystems.ai/mcp"
}
}
}
Claude Code
claude mcp add agentic-platform --transport http https://platform.crestsystems.ai/mcp
Docker
docker run -p 8080:8080 ghcr.io/andysalvo/agentic-platform:latest
Works with Claude Desktop, Claude Code, VS Code, Cursor, Cline, and any MCP-compatible client.
Free Tools (No API Key Needed)
| Tool | What It Does |
|---|---|
mcp_manifest_lint | The only MCP linter. Validate your tool definitions for anti-patterns, missing fields, bad descriptions, and schema issues. Pass/fail report with fixes. |
agent_health_check | Score your agent's system prompt on governance and best practices (0-100). Detailed diagnostic with specific issues and remediation. |
estimate_agent_cost | Compare costs across Claude, GPT, Gemini, and other models. Per-call, per-run, and per-day breakdown with optimization tips. |
Expert Skills (Free Tier: 10 Calls/Day)
| Skill | Description |
|---|---|
governance | Design agent systems that preserve human authority. 3 core invariants, Coupled Authority Phenomenon, 14 forbidden failure modes. |
agentic-economics | Pricing models, unit economics, and revenue architecture for AI agent platforms. Market projections, cost-to-serve benchmarks (March 2026). |
intent-architecture | Build deterministic, auditable systems. Append-only decision logs, 9 system invariants, implementation patterns, embodiment tests. |
Quick Start
1. mcp_manifest_lint(tools_json='[{"name":"my_tool","description":"Does something"}]')
-> Pass/fail report with specific fixes
2. agent_health_check(system_prompt="Your agent's system prompt here")
-> Score 0-100 with detailed diagnostic
3. estimate_agent_cost(model="claude-sonnet-4", input_tokens=2000, output_tokens=1000, num_calls=10)
-> Cost comparison table across all major models
Pricing
- Free tools: Unlimited. No API key needed.
- Expert skills: 10 free calls/day per API key.
- Credit packs: $5 (50 credits) or $20 (250 credits) via Stripe.
Crest Service Fleet
| Service | URL | Purpose |
|---|---|---|
| Verify API | verify.crestsystems.ai | Conformance verification for x402 action_ref. Submit receipts, get signed verdicts with public permalinks. |
| Trust Check | supership.crestsystems.ai/check | Free pre-payment trust oracle for x402 agent commerce. |
| Conformance | crestsystems.ai/conformance | Public conformance results matrix for action-ref-v1. |
| x402 Audit | audit.crestsystems.ai | Smart contract audit, code scan, wallet risk profiling ($0.25-$1.00 USDC). |
| x402 Data | data.crestsystems.ai | Crypto market data ($0.01/call USDC on Base). |
Governance
This platform operates under three core invariants:
- No Silent Inference -- no inferring or reinterpreting input without explicit documentation
- Auditability at the Decision Level -- every state change traceable to a decision
- Explicit Authority Transfer -- all commitments require explicit authorization
These apply to the platform itself, not just its users.
Keywords
MCP server, MCP linter, MCP validator, MCP manifest lint, agent governance, agent health check, agent cost estimator, AI agent tools, Model Context Protocol, MCP tool validation, agent diagnostics, governance scoring, x402 conformance, action-ref verification, agent accountability, trust oracle, agent commerce
License
MIT
Built By
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
