Skip to main content
Glama
semanticintent

Semantic Perch Intelligence MCP

by semanticintent
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Remote

Semantic Perch Intelligence MCP

License: MIT CI TypeScript Node.js Tests

Semantic Intent Hexagonal Architecture PRs Welcome

PerchIQX - Deep Insights. Database Intelligence.

A Model Context Protocol (MCP) server for Cloudflare D1 database introspection. Reference implementation of Semantic Intent patterns demonstrating semantic anchoring, observable properties, and domain-driven design for AI-assisted database development.

📚 Table of Contents

Related MCP server: mcp-db-schema-tools

🎯 What Makes This Different

This isn't just another database introspection tool—it's a reference implementation of proven semantic intent patterns:

  • ✅ Semantic Anchoring: Schema analysis based on meaning (table purpose, relationships), not technical metrics (row counts, sizes)

  • ✅ Observable Properties: Decisions anchored to directly observable schema markers (foreign keys, indexes, constraints)

  • ✅ Intent Preservation: Database semantics maintained through all transformations (development → staging → production)

  • ✅ Domain Boundaries: Clear semantic ownership (Schema Domain ≠ Query Optimization Domain ≠ MCP Protocol Domain)

Built on research from Semantic Intent as Single Source of Truth, this implementation demonstrates how to build maintainable, AI-friendly database tools that preserve intent.

🚀 Quick Start

Prerequisites

  • Node.js 20.x or higher

  • Cloudflare account with D1 databases

  • Cloudflare API token with D1 access

Installation

  1. Clone the repository

    git clone https://github.com/semanticintent/semantic-perch-intelligence-mcp.git
cd semantic-perch-intelligence-mcp

  2. Install dependencies

    npm install

  3. Configure environment

    Copy the example configuration:

    cp .env.example .env

    Update .env with your Cloudflare credentials:

    # Cloudflare Configuration
CLOUDFLARE_ACCOUNT_ID=your_cloudflare_account_id
CLOUDFLARE_API_TOKEN=your_cloudflare_api_token

# D1 Database Configuration - Development
D1_DEV_DATABASE_ID=your_dev_database_id
D1_DEV_DATABASE_NAME=your_dev_database_name

# D1 Database Configuration - Staging (Optional)
D1_STAGING_DATABASE_ID=your_staging_database_id
D1_STAGING_DATABASE_NAME=your_staging_database_name

# D1 Database Configuration - Production (Optional)
D1_PROD_DATABASE_ID=your_prod_database_id
D1_PROD_DATABASE_NAME=your_prod_database_name

    Note: At least one database environment must be configured.

  4. Build the server

    npm run build

  5. Start the MCP server

    npm start

    Or use the provided shell script:

    ./start-d1-mcp.sh

Get Cloudflare API Token

  1. Go to Cloudflare Dashboard

  2. Navigate to My Profile → API Tokens

  3. Click Create Token

  4. Use the Edit Cloudflare Workers template

  5. Add D1 permissions: D1:Read

  6. Copy the token to your .env file

Get D1 Database IDs

# List all your D1 databases
wrangler d1 list

# Get specific database info
wrangler d1 info <database-name>

Copy the database IDs to your .env file.

🛠️ MCP Tools

This server provides 4 comprehensive MCP tools for D1 database introspection:

1. analyze_database_schema

Analyze complete database schema structure with metadata and optional sample data.

Parameters:

  • environment (required): "development" | "staging" | "production"

  • includeSamples (optional, default: true): Include sample data from tables

  • maxSampleRows (optional, default: 5): Maximum rows per table sample

Returns:

  • Complete schema analysis

  • Table structures with columns, types, constraints

  • Indexes and foreign keys

  • Sample data from each table (if enabled)

  • Schema metadata and statistics

Example:

{
  "name": "analyze_database_schema",
  "arguments": {
    "environment": "development",
    "includeSamples": true,
    "maxSampleRows": 5
  }
}

2. get_table_relationships

Extract and analyze foreign key relationships between tables.

Parameters:

  • environment (required): Database environment

  • tableName (optional): Filter relationships for specific table

Returns:

  • Foreign key relationships with cardinality (one-to-many, many-to-one)

  • Referential integrity rules (CASCADE, SET NULL, etc.)

  • Relationship metadata and statistics

Example:

{
  "name": "get_table_relationships",
  "arguments": {
    "environment": "production",
    "tableName": "users"
  }
}

3. validate_database_schema

Validate database schema for common issues and anti-patterns.

Parameters:

  • environment (required): Database environment

Returns:

  • Schema validation results

  • Missing primary keys

  • Foreign keys without indexes

  • Naming convention violations

  • Tables without relationships

Example:

{
  "name": "validate_database_schema",
  "arguments": {
    "environment": "production"
  }
}

4. suggest_database_optimizations

Generate schema optimization recommendations based on structure analysis.

Parameters:

  • environment (required): Database environment

Returns:

  • Prioritized optimization suggestions (high/medium/low)

  • Missing index recommendations

  • Primary key suggestions

  • Schema improvement opportunities

  • Performance optimization tips

Example:

{
  "name": "suggest_database_optimizations",
  "arguments": {
    "environment": "production"
  }
}

🔌 Connect to Claude Desktop

Connect this MCP server to Claude Desktop for AI-assisted database development.

Configuration

  1. Edit Claude Desktop config - Go to Settings → Developer → Edit Config

  2. Add MCP server configuration:

{
  "mcpServers": {
    "semantic-perch": {
      "command": "node",
      "args": [
        "/absolute/path/to/semantic-perch-intelligence-mcp/dist/index.js"
      ],
      "env": {
        "CLOUDFLARE_ACCOUNT_ID": "your_account_id",
        "CLOUDFLARE_API_TOKEN": "your_api_token",
        "D1_DEV_DATABASE_ID": "your_dev_db_id",
        "D1_DEV_DATABASE_NAME": "your_dev_db_name",
        "D1_STAGING_DATABASE_ID": "your_staging_db_id",
        "D1_STAGING_DATABASE_NAME": "your_staging_db_name",
        "D1_PROD_DATABASE_ID": "your_prod_db_id",
        "D1_PROD_DATABASE_NAME": "your_prod_db_name"
      }
    }
  }
}

  1. Restart Claude Desktop

  2. Verify tools are available - You should see 4 D1 tools in Claude's tool list

Usage Example

In Claude Desktop:

"Analyze my production database schema and suggest optimizations for tables with foreign keys"

Claude will use the analyze_database_schema and suggest_database_optimizations tools automatically.

🏗️ Architecture

This project demonstrates Domain-Driven Hexagonal Architecture with clean separation of concerns:

┌─────────────────────────────────────────────────────────┐
│                   Presentation Layer                     │
│              (MCP Server - Protocol Handling)            │
└────────────────────┬────────────────────────────────────┘
                     │
┌────────────────────▼────────────────────────────────────┐
│                  Application Layer                       │
│        (Use Cases - Schema Analysis Orchestration)      │
└────────────────────┬────────────────────────────────────┘
                     │
┌────────────────────▼────────────────────────────────────┐
│                    Domain Layer                          │
│     (Schema Entities, Relationship Logic, Services)     │
│              Pure Business Logic                         │
└────────────────────┬────────────────────────────────────┘
                     │
┌────────────────────▼────────────────────────────────────┐
│                Infrastructure Layer                      │
│       (Cloudflare D1 REST API, HTTP Client)             │
│           Technical Adapters                             │
└─────────────────────────────────────────────────────────┘

Implementation Status

Status: ✅ Hexagonal architecture refactoring complete

Current Structure:

src/
├── domain/              # Business logic (entities, services)
│   ├── entities/        # DatabaseSchema, TableInfo, Column, etc.
│   ├── services/        # SchemaAnalyzer, RelationshipAnalyzer, etc.
│   ├── repositories/    # Port interfaces
│   └── value-objects/   # Environment enum
├── application/         # Use cases and orchestration
│   ├── use-cases/       # AnalyzeSchema, GetRelationships, etc.
│   └── ports/           # Cache provider interface
├── infrastructure/      # External adapters
│   ├── adapters/        # CloudflareD1Repository, Cache
│   ├── config/          # CloudflareConfig, DatabaseConfig
│   └── http/            # CloudflareAPIClient
├── presentation/        # MCP protocol layer
│   └── mcp/             # D1DatabaseMCPServer
└── index.ts             # Composition root (DI)

See ARCHITECTURE.md for detailed design documentation.

Layer Responsibilities

Domain Layer:

  • Database schema entities (Schema, Table, Relationship, Index)

  • Schema analysis business logic

  • Relationship extraction logic

  • Optimization recommendation rules

Application Layer:

  • Orchestrate domain services

  • Execute use cases (AnalyzeSchema, GetRelationships, etc.)

  • Coordinate infrastructure adapters

Infrastructure Layer:

  • Cloudflare D1 REST API integration

  • HTTP client for API calls

  • Cache provider (in-memory)

Presentation Layer:

  • MCP server initialization

  • Tool registration and routing

  • Request/response formatting

Semantic Intent Principles

This codebase follows strict semantic anchoring rules:

  1. Semantic Over Structural

    // ✅ SEMANTIC: Based on observable schema properties
const needsIndex = table.hasForeignKey() && !table.hasIndexOnForeignKey()

// ❌ STRUCTURAL: Based on technical metrics
const needsIndex = table.rowCount > 10000 && table.queryCount > 100

  2. Intent Preservation

    // ✅ Environment semantics preserved through transformations
const schema = await fetchSchema(Environment.PRODUCTION)
// Schema analysis preserves "production" intent - no overrides

  3. Observable Anchoring

    // ✅ Based on directly observable properties
const relationships = extractForeignKeys(sqliteMaster)

// ❌ Based on inferred behavior
const relationships = inferFromQueryPatterns(logs)

See SEMANTIC_ANCHORING_GOVERNANCE.md for complete governance rules.

🧪 Testing

Status: ✅ Comprehensive test suite with 398 tests passing

Test Coverage

  • ✅ Domain Layer: 212 tests (entities, services, validation)

  • ✅ Infrastructure Layer: 64 tests (D1 adapter, API client, config)

  • ✅ Application Layer: 35 tests (use cases, orchestration)

  • ✅ Presentation Layer: 13 tests (MCP server, tool routing)

  • ✅ Integration: 15 tests (end-to-end flows)

  • ✅ Value Objects: 59 tests (Environment, immutability)

Total: 398 tests (all passing ✅)

Running Tests

# Run all tests
npm test

# Watch mode
npm run test:watch

# With UI
npm run test:ui

# Coverage report
npm run test:coverage

Test Framework

  • Vitest: Fast unit testing framework

  • @vitest/coverage-v8: Code coverage reports

  • Mock Strategy: Mock Cloudflare D1 API responses via interface implementations

📖 Learning from This Implementation

This codebase serves as a reference implementation for semantic intent patterns in database tooling.

Key Files to Study

Hexagonal Architecture Implementation:

Reference Documentation:

Related Projects

🤝 Contributing

We welcome contributions! This is a reference implementation, so contributions should maintain semantic intent principles.

How to Contribute

  1. Read the guidelines: CONTRIBUTING.md

  2. Check refactoring plan: D1_MCP_REFACTORING_PLAN.md

  3. Follow the architecture: Maintain layer boundaries and semantic anchoring

  4. Add tests: All changes need comprehensive test coverage

  5. Document intent: Explain WHY, not just WHAT

Contribution Standards

  • ✅ Follow semantic intent patterns

  • ✅ Maintain hexagonal architecture (post-refactoring)

  • ✅ Add comprehensive tests (90%+ coverage target)

  • ✅ Include semantic documentation

  • ✅ Pass all CI checks

Quick Links:

Community

🔒 Security

Security is a top priority. Please review our Security Policy for:

  • API token management best practices

  • What to commit / what to exclude

  • Reporting security vulnerabilities

  • Security checklist for deployment

Found a vulnerability? Email: security@semanticintent.dev

🔬 Research Foundation

This implementation is based on the research paper "Semantic Intent as Single Source of Truth: Immutable Governance for AI-Assisted Development".

Core Principles Applied

  1. Semantic Over Structural - Schema analysis based on meaning, not metrics

  2. Intent Preservation - Environment semantics maintained through transformations

  3. Observable Anchoring - Decisions based on directly observable schema properties

  4. Immutable Governance - Protect semantic integrity at runtime

Related Resources

📊 Project Roadmap

✅ Phase 0: Initial Implementation (Complete)

  • Monolithic MCP server with 6 tools

  • D1 REST API integration

  • Basic schema analysis

✅ Phase 1: Domain Layer (Complete)

  • 10 domain entities with semantic validation

  • 3 domain services (SchemaAnalyzer, RelationshipAnalyzer, OptimizationService)

  • 212 passing tests

✅ Phase 2: Infrastructure Layer (Complete)

  • CloudflareD1Repository adapter

  • CloudflareAPIClient HTTP client

  • InMemoryCacheProvider

  • 64 passing tests

✅ Phase 3: Application Layer (Complete)

  • 4 use cases (AnalyzeSchema, GetRelationships, ValidateSchema, SuggestOptimizations)

  • Port interfaces (ICloudflareD1Repository, ICacheProvider)

  • 35 passing tests

✅ Phase 4: Presentation Layer (Complete)

  • D1DatabaseMCPServer with 4 MCP tools

  • Request/response DTOs

  • 13 passing tests

✅ Phase 5: Integration & Composition Root (Complete)

  • Dependency injection in index.ts

  • Environment configuration

  • 15 integration tests

✅ Phase 6: CI/CD & Documentation (Complete)

  • TypeScript build verification

  • README updated

  • 398 total tests passing

🎯 Phase 7: Production Readiness (Planned)

  • GitHub Actions CI/CD workflow

  • Dependabot automation

  • Security scanning

  • GitHub repository setup

See D1_MCP_REFACTORING_PLAN.md for detailed roadmap.

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

This is a reference implementation demonstrating semantic intent patterns for database introspection. Study the code, learn the patterns, and apply them to your own projects. 🏗️

Available Tools

5 tools
analyze_database_schemaB

Analyze D1 database schema structure, tables, columns, indexes, and relationships with optional sample data

ParametersJSON Schema
NameRequiredDescriptionDefault
environmentYesDatabase environment to analyze
maxSampleRowsNoMaximum number of sample rows per table
includeSamplesNoInclude sample data from tables (max 5 rows per table)

TDQS

B3.2/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must carry the full burden of behavioral disclosure. It says 'Analyze' which implies a read-only operation, but doesn't explicitly state that it won't modify anything, nor does it mention potential performance impacts of sampling data or usage on production environments. This lack of detail is a significant gap for a tool with zero annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence of about 15 words, front-loaded with the verb and resource. Every word is informative, with no redundancy or filler. It is well-structured and immediately conveys the tool's purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description should explain what the analysis returns (e.g., a report, schema representation, or diagnostics). It does not. Given the tool has 3 parameters and covers multiple aspects of the schema, the description is incomplete. It also fails to mention any caveats like environment differences or performance considerations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description mentions 'optional sample data', which aligns with includeSamples and maxSampleRows, but adds no additional semantic detail beyond what the input schema already provides. It neither clarifies parameter formats nor explains edge cases.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Analyze' and the resource 'D1 database schema', listing specific aspects (tables, columns, indexes, relationships) and optional sample data. It distinguishes this from sibling tools like get_table_relationships by its broader scope, though it doesn't explicitly contrast with them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for general schema analysis, but provides no explicit guidance on when to use this tool versus siblings like validate_database_schema or suggest_schema_optimizations. There are no exclusions or alternative recommendations, so using it is inferred rather than directed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

compare_schemasA

Compare database schemas between environments to detect drift and plan migrations with ICE-scored differences

ParametersJSON Schema
NameRequiredDescriptionDefault
sourceDatabaseIdYesSource database ID to compare from
targetDatabaseIdYesTarget database ID to compare to
sourceEnvironmentYesSource database environment
targetEnvironmentYesTarget database environment

TDQS

A4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It discloses that the tool outputs ICE-scored differences and is used for migration planning, but it does not state whether the operation is read-only, any side effects, permissions needed, or what ICE-scored means. This adds some context beyond the name but leaves notable gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that efficiently conveys the action, resource, and purpose without fluff. Every word contributes value, making it highly concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 4 required parameters, no output schema, and no annotations, the description provides a clear purpose and mentions the ICE-scored output. However, it leaves some gaps: 'ICE-scored' is unexplained, and the phrase 'between environments' could be more precise given that the actual parameters are database IDs. Overall, it is fairly complete but not exhaustive.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema descriptions cover all 4 parameters (100% coverage), so the baseline is 3. The description adds no parameter-specific details beyond the general 'between environments' concept, which is already reflected in the schema's environment enums.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb (Compare), the resource (database schemas), and the scope (between environments), while also specifying the purpose (detect drift, plan migrations) and the distinctive output (ICE-scored differences). This effectively differentiates it from sibling tools like analyze_database_schema or validate_database_schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use the tool (comparing schemas across environments for drift detection or migration planning) and provides clear context. However, it does not explicitly mention when not to use it or name alternatives, which would elevate it to a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_table_relationshipsB

Extract and analyze foreign key relationships between tables in the database

ParametersJSON Schema
NameRequiredDescriptionDefault
tableNameNoOptional: Filter relationships for specific table
environmentYesDatabase environment to analyze

TDQS

B3.2/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations available, the description carries the full burden of disclosure. It does not state whether the operation is read-only, what side effects might occur, what output format to expect, or any other behavioral traits. The vague 'analyze' adds little transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence that is front-loaded with the tool's purpose. No unnecessary words or repetition, making it appropriately concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having a simple schema, the tool has no output schema, so the description should explain what the return value looks like and what 'analyze' entails. It does not, leaving the agent without critical context for interpreting results or understanding the tool's full behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with both parameters already explained (tableName filter and environment). The description adds no additional meaning to the parameters, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function with a specific verb ('Extract and analyze') and resource ('foreign key relationships between tables'), and it distinguishes itself from sibling tools that focus on broader schema analysis, validation, optimization, or comparison.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives, no exclusions or prerequisites are mentioned. The description implies usage through its purpose but offers no explicit context or contrast with sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

suggest_schema_optimizationsB

Analyze schema and suggest performance optimizations (missing indexes, redundant indexes, etc.)

ParametersJSON Schema
NameRequiredDescriptionDefault
environmentYesDatabase environment to analyze for optimizations

TDQS

B3.3/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It implies a read-only analysis ('analyze and suggest'), but does not explicitly state that it makes no changes, nor does it describe the output format or any permissions/limitations. This leaves significant behavioral ambiguity.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, focused sentence with parenthetical examples. It is front-loaded with the core action and contains no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with one enum parameter, the description plus schema provides a basic understanding. However, the lack of usage guidance, explicit read-only nature, and output expectations leaves gaps that a more complete description would fill. The 'etc.' hints at additional optimizations but does not elaborate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage: the sole parameter 'environment' is well-described with an enum list, so the schema already conveys complete parameter semantics. The description does not add further parameter detail, but none is needed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific action ('Analyze schema and suggest performance optimizations') with concrete examples ('missing indexes, redundant indexes'). It is distinguishable from siblings like validate_database_schema or compare_schemas, though it could more explicitly contrast with analyze_database_schema, which may also analyze schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is implied: the tool is for suggesting performance optimizations, not for general schema analysis or validation. However, there is no explicit guidance on when to choose this over analyze_database_schema or other siblings, nor any exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

validate_database_schemaB

Validate database schema integrity and detect potential issues (missing primary keys, orphaned foreign keys, etc.)

ParametersJSON Schema
NameRequiredDescriptionDefault
environmentYesDatabase environment to validate

TDQS

B3.2/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full responsibility for disclosing behavioral traits. It states what the tool detects but does not mention whether it is read-only, whether it modifies data, what the output format is, or if it requires special permissions. This is a meaningful gap for a validation tool that could potentially be expected to run side-effect-free checks.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that front-loads the primary action ('Validate database schema integrity') and then provides concrete examples to clarify scope. There is no redundant wording or filler, and every part of the sentence contributes useful information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has no output schema and no annotations, yet the description does not explain what the result looks like or how issues are reported. Given the presence of sibling tools with overlapping purposes, the description also fails to clarify the tool's unique position. While the single parameter is well-documented, the lack of return-value or behavioral context leaves the description incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% schema description coverage: the single parameter 'environment' is fully described with an enum of valid values and a clear meaning. The description adds no additional semantic detail beyond the schema, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Validate') with a clear resource ('database schema') and enumerates concrete examples of what it checks (missing primary keys, orphaned foreign keys). This distinguishes it from related sibling tools like analyze_database_schema and suggest_schema_optimizations, which imply broader or different scopes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no explicit guidance on when to use this tool versus alternatives such as analyze_database_schema or compare_schemas. It does not mention any exclusions, prerequisites, or scenarios where another tool would be preferred, leaving the agent to infer usage solely from the tool name and purpose.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 5 tool updatesv2.0.0
    • First observedanalyze_database_schema
    • First observedcompare_schemas
    • First observedget_table_relationships
    • First observedsuggest_schema_optimizations
    • First observedvalidate_database_schema
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.7/5.0
Disambiguation4/5

The tools are largely distinct, but there is some overlap between 'analyze_database_schema' and 'get_table_relationships', where the former includes relationships as part of its analysis. However, each tool has a clear primary focus, so an agent can usually select the right one based on context.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern: analyze, get, validate, suggest, compare. The naming is predictable and makes it easy to infer the action and target of each tool.

Tool Count5/5

With 5 tools, the server is well-scoped for its stated purpose of database schema intelligence. Each tool covers a distinct aspect without redundancy, making the surface area manageable.

Completeness5/5

The tool set covers the full lifecycle of schema analysis: inspection, relationship mapping, validation, optimization suggestions, and comparison. There are no obvious gaps for the intended functionality.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • Semantic D1 MCP by semanticintent

    Semantic D1 MCPofficial

    semanticintent
    A
    license
    A
    quality
    D
    maintenance
    Enables AI-assisted analysis and optimization of Cloudflare D1 databases through comprehensive schema introspection, relationship mapping, validation, and optimization recommendations. Demonstrates semantic intent patterns with hexagonal architecture for maintainable database development workflows.
    4
    3
    MIT

  • mcp-db-schema-tools

    southglory
    A
    license
    Not graded
    quality
    D
    maintenance
    Database schema management MCP server for Claude Code, enabling natural language management from business requirements to complete databases.
    MIT

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/semanticintent/semantic-perch-intelligence-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server