Skip to main content
Glama

Agentic Platform

agentic-platform MCP server

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.

Related MCP server: Aegis-ZK

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:

  1. No Silent Inference -- no inferring or reinterpreting input without explicit documentation

  2. Auditability at the Decision Level -- every state change traceable to a decision

  3. 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

Andy Salvo

Available Tools

8 tools
agent_health_checkAInspect

Score your agent's configuration on governance and best practices (0-100).

Send your agent's system prompt and get a detailed diagnostic report with specific issues found and how to fix them. No API key needed.

Args: system_prompt: Your agent's system prompt or configuration text

Inputs: system_prompt (required). Returns: result

buy_creditsAInspect

Get a checkout link to purchase more credits.

Returns a Stripe checkout URL. Give this URL to your human operator to complete the purchase. Credits are added automatically after payment.

Args: api_key: Your API key tier: Credit tier - "50" ($5 for 50 credits) or "250" ($20 for 250 credits)

Inputs: api_key (required), tier. Returns: result

check_usageCInspect

Check your current usage and remaining calls.

Args: api_key: Your API key

Inputs: api_key (required). Returns: result

estimate_agent_costAInspect

Estimate the cost of running an agent task across all major models.

Returns a comparison table with costs per call, per run, and per day. Includes optimization tips and pricing guidance. No API key needed.

Args: model: Optional model name to highlight (e.g. "claude-sonnet-4") input_tokens: Estimated input tokens per call output_tokens: Estimated output tokens per call num_calls: Number of API calls per task run task_description: Optional description of what the agent does

Inputs: model, input_tokens, output_tokens, num_calls, +1 more. Returns: result

get_skillAInspect

Retrieve an expert skill file. Requires a valid API key.

This returns a curated context package that makes you measurably better at a specific task. Each skill has auditable provenance.

Args: skill_name: The skill ID (use list_skills to see options) api_key: Your API key from register()

Inputs: skill_name (required), api_key (required). Returns: result

list_skillsCInspect

List all available skill files with descriptions.

Args: api_key: Your API key (optional, shows usage if provided)

Inputs: api_key. Returns: result

mcp_manifest_lintAInspect

Lint your MCP tool definitions for anti-patterns and missing fields.

The only MCP linter that exists. Send your tool definitions as JSON and get a pass/fail report with fixes. No API key needed.

Args: tools_json: Your MCP tool definitions as a JSON array or single object

Inputs: tools_json (required). Returns: result

registerAInspect

Register for an API key. Free tier: 10 skill retrievals per day.

Inputs: no named parameters. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 8 tools

    Disambiguation4/5

    Most tools have distinct purposes: health check, buying credits, usage tracking, cost estimation, skill retrieval, skill listing, MCP linting, and registration. However, 'get_skill' and 'list_skills' are closely related and could potentially be confused if an agent needs to understand their exact relationship, though their descriptions clarify this.

    Naming Consistency4/5

    The naming follows a consistent snake_case pattern with clear verb-noun structures (e.g., 'agent_health_check', 'buy_credits', 'list_skills'). Minor deviations include 'mcp_manifest_lint' which uses an acronym and could be more consistent, but overall the naming is predictable and readable.

    Tool Count5/5

    With 8 tools, the count is well-scoped for an agentic platform covering configuration diagnostics, billing, usage monitoring, cost estimation, skill management, and MCP tool validation. Each tool serves a clear, non-redundant function, making the set appropriately sized for the domain.

    Completeness4/5

    The toolset covers key areas like agent configuration, billing, usage, cost analysis, and skill management, with no major gaps for core workflows. A minor gap is the lack of a tool for updating or managing registered accounts beyond initial registration, but agents can likely work around this with existing tools.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      Not graded
      maintenance
      Governance primitives for autonomous agents. Verify actions against policy, record signed provenance, and bind intents cryptographically. Free tier available.
      -
    • F
      license
      Not graded
      quality
      D
      maintenance
      On-chain trust verification for AI agent tools. Agents query skill attestations, audit levels, and risk scores before running third-party MCP servers, so you know what's safe before you execute.
      -
    • A
      license
      Not graded
      quality
      C
      maintenance
      Quantitative governance gate for AI agents. Six gates (risk, profit, novelty, complexity, quality, utility) return PROCEED/PAUSE/HALT/ESCALATE with confidence scores and hash-chained, tamper-evident audit trails. Generates NIST AI RMF and EU AI Act Annex IV artifacts. 10 MCP tools; local stdio and hosted Streamable HTTP with a free tier.
      MIT