Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCP Migration Advisor Analyze this migration for risks: ALTER TABLE users DROP COLUMN email;"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server for database migration risk analysis. Detects dangerous schema changes before they hit production.
Database migration failures cause outages. This tool analyzes your Flyway and Liquibase migrations before they run — detecting destructive operations, lock risks, and data loss patterns.
Unlike MigrationPilot (PG-only, raw SQL analysis), this tool parses Liquibase XML and YAML changelogs natively — extracting changeSets, detecting conflicts between changeSet IDs, and validating rollback completeness. It works across database types, not just PostgreSQL.
Related MCP server: migratoor
Lock Risk Analysis: Detects DDL operations that acquire heavy table locks (ACCESS EXCLUSIVE, SHARE locks)
Data Loss Detection: Finds column drops, type changes that truncate, TRUNCATE/DELETE without WHERE
Risk Scoring: Calculates 0-100 risk score based on severity of detected issues
Flyway Support: Parses V__*.sql and R__*.sql migration filenames
Liquibase Support: Parses XML and YAML changelogs with changeSet extraction
Conflict Detection: Identifies duplicate changeSet IDs and ordering issues
Rollback Validation: Checks rollback completeness for each changeSet
Actionable Recommendations: Every risk includes a specific safe alternative
Generate exportable diagnostic reports (HTML + PDF) with a Pro license key.
Full JVM thread dump analysis report with actionable recommendations
PDF export for sharing with your team
Priority support
$9.00/month — Get Pro License
Pro license key activates the generate_report MCP tool in mcp-jvm-diagnostics.
npx mcp-migration-advisorOr install globally:
npm install -g mcp-migration-advisorAdd to ~/.claude/claude_desktop_config.json:
{
"mcpServers": {
"migration-advisor": {
"command": "npx",
"args": ["-y", "mcp-migration-advisor"]
}
}
}Try these prompts in Claude:
"Analyze this migration for risks: ALTER TABLE users DROP COLUMN email;" — Returns risk score (0-100), lock risks, data loss warnings, and safe alternatives
"Generate a rollback for this migration: CREATE TABLE orders (...); CREATE INDEX idx_orders_user ON orders(user_id);" — Produces reverse DDL in correct order
"Score this Liquibase changelog: [paste XML]" — Parses changeSets and calculates overall risk
analyze_migrationFull analysis of a SQL migration file. Returns lock risks, data loss analysis, and recommendations.
Parameters:
filename — Migration filename (e.g., V2__add_user_email.sql)
sql — The SQL content
analyze_liquibaseFull analysis of a Liquibase XML changelog. Parses changeSets and applies the same lock risk and data loss analysis.
Parameters:
xml — The Liquibase XML changelog content
analyze_liquibase_yamlFull analysis of a Liquibase YAML changelog. Parses changeSets from YAML format and applies the same lock risk and data loss analysis. Supports all standard change types: createTable, dropTable, addColumn, dropColumn, modifyDataType, createIndex, renameTable, renameColumn, and more.
Parameters:
yaml — The Liquibase YAML changelog content
score_riskQuick risk score (0-100) with verdict (LOW/MODERATE/HIGH RISK).
Parameters:
filename — Migration filename
sql — The SQL content
generate_rollbackGenerate reverse DDL to undo a SQL migration. Produces rollback SQL with warnings for irreversible operations.
Parameters:
filename — Migration filename
sql — The SQL content
Reverses automatically:
CREATE TABLE → DROP TABLE
ADD COLUMN → ALTER TABLE ... DROP COLUMN
CREATE INDEX → DROP INDEX (preserves CONCURRENTLY)
ADD CONSTRAINT → DROP CONSTRAINT
SET NOT NULL → DROP NOT NULL
RENAME → reverse RENAME
Warns on irreversible:
DROP TABLE, DROP COLUMN (data loss)
Column type changes (original type unknown)
DROP INDEX, DROP CONSTRAINT (original definition unknown)
Includes Flyway schema_history cleanup statement.
detect_conflictsDetect conflicts between two SQL migration files. Identifies same-table modifications, same-column changes, lock contention risks, and drop dependencies that could cause failures if applied concurrently or in the wrong order.
Parameters:
filename_a — First migration filename (e.g., V3__add_email.sql)
sql_a — SQL content of the first migration
filename_b — Second migration filename (e.g., V4__modify_users.sql)
sql_b — SQL content of the second migration
Detects:
Same column conflicts (CRITICAL) — both migrations modify the same column on the same table
Drop dependencies (CRITICAL) — one migration drops a table the other modifies, causing order-dependent failures
Lock contention (WARNING) — both migrations require exclusive locks on the same table, risking lock wait timeouts
Returns a conflict report with severity levels, affected tables/columns, and whether the migrations can safely run concurrently.
Pattern | Severity | Why It's Dangerous |
NOT NULL without DEFAULT | CRITICAL | Full table rewrite with ACCESS EXCLUSIVE lock |
Column type change | CRITICAL | Table rewrite, data truncation risk |
CREATE INDEX (not CONCURRENTLY) | HIGH | SHARE lock blocks all writes |
DROP TABLE CASCADE | CRITICAL | Drops all dependent objects |
DROP COLUMN | HIGH | Irreversible data loss |
SET NOT NULL | HIGH | Full table scan with lock |
FOREIGN KEY constraint | MEDIUM | Locks both tables for validation |
TRUNCATE / DELETE without WHERE | CERTAIN data loss | All rows permanently deleted |
Static analysis only: Analyzes SQL text without database connectivity. Cannot check actual table sizes, row counts, or existing schema to calibrate risk.
PostgreSQL-focused: Lock risk recommendations are primarily for PostgreSQL. MySQL and SQLite lock behaviors differ and may not be fully covered.
Complex DDL: Stored procedures, triggers, and dynamic SQL within migrations are classified as "OTHER" and receive generic risk assessment.
Liquibase support: Handles standard XML and YAML changesets. JSON Liquibase format and custom change types are not supported.
Rollback limitations: Auto-generated rollbacks cannot reverse DROP TABLE, DROP COLUMN, or type changes (data is lost). These produce warnings instead of rollback SQL.
Multi-statement transactions: The parser splits on semicolons. Statements containing semicolons inside strings or dollar-quoted blocks may be split incorrectly.
No execution: The advisor analyzes but never executes migrations. All recommendations are advisory.
Database-specific DDL: Parser targets PostgreSQL/MySQL DDL syntax. Oracle PL/SQL or SQL Server T-SQL may not be fully recognized.
mcp-db-analyzer — PostgreSQL/MySQL/SQLite schema analysis
mcp-spring-boot-actuator — Spring Boot health, metrics, and bean analysis
mcp-jvm-diagnostics — Thread dump and GC log analysis
mcp-redis-diagnostics — Redis memory, slowlog, and client diagnostics
MIT
End-of-life: 2026-05-10.
This MCP server is no longer maintained or distributed. The Corporation
has pivoted to Apify marketplace actors. See
irrationalways on Apify and
irrcorp/bzp-poland-tenders for current Corporation work.
The npm package has been unpublished. The repository is archived for historical reference only.
Analyze a Liquibase XML changelog for lock risks, data loss potential, and unsafe patterns. Supports all major change types: createTable, dropTable, addColumn, dropColumn, modifyDataType, addNotNullConstraint, createIndex, dropIndex, addForeignKeyConstraint, dropForeignKeyConstraint, renameTable, renameColumn. Inline changeSets are also analyzed for TRUNCATE, DELETE without WHERE, and UPDATE without WHERE. Returns lock risk severity (ACCESS EXCLUSIVE, SHARE locks) and data loss risk per operation.
| Name | Required | Description | Default |
|---|---|---|---|
| xml | Yes | The Liquibase XML changelog content |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Given no annotations, the description reveals behavioral traits well: it details the analysis scope (lock risks, data loss, unsafe patterns) and specifies lock types (ACCESS EXCLUSIVE, SHARE). However, it does not explicitly state that the tool is read-only and has no side effects, which would be helpful.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and well-structured: it front-loads the primary purpose, lists supported change types in a bullet-like manner, and mentions output details. Every sentence adds value without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is fairly complete for a simple tool with one parameter and no output schema. It covers input, analysis scope, and types of returns (lock risk severity, data loss risk). However, it lacks detail on the output format or structure, which is necessary since there is no output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the schema already describes the 'xml' parameter. The description reinforces that the input is a Liquibase XML changelog but adds no new semantic details beyond what the schema provides. Baseline score is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Analyze a Liquibase XML changelog for lock risks, data loss potential, and unsafe patterns.' It lists supported change types and inline SQL analysis, making it specific and distinct from siblings like analyze_liquibase_yaml.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage context is implied (use when analyzing Liquibase XML changelogs), but no explicit guidance on when not to use it or how to choose among siblings like analyze_migration or analyze_liquibase_yaml. This leaves ambiguity for an AI agent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Analyze a Liquibase YAML changelog for lock risks, data loss potential, and unsafe patterns. Supports all major change types: createTable, dropTable, addColumn, dropColumn, modifyDataType, addNotNullConstraint, createIndex, dropIndex, addForeignKeyConstraint, dropForeignKeyConstraint, renameTable, renameColumn. Inline sql changeSets are also analyzed for TRUNCATE, DELETE without WHERE, and UPDATE without WHERE. Returns lock risk severity (ACCESS EXCLUSIVE, SHARE locks) and data loss risk per operation.
| Name | Required | Description | Default |
|---|---|---|---|
| yaml | Yes | The Liquibase YAML changelog content |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Since no annotations are provided, the description fully discloses behavioral traits: it analyzes for lock risks, data loss, and unsafe patterns, and returns severity levels. It does not explicitly state that it is read-only, but the analysis nature implies no side effects, which is sufficient for transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and well-structured: three sentences front-loaded with purpose, supported features, and outputs. Every sentence adds value without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (single parameter, no output schema, no annotations), the description covers purpose, supported change types, and outputs. It could mention output format or limitations (e.g., only YAML) but is sufficiently complete for the complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 100% schema description coverage, the schema already describes the single parameter 'yaml' as 'The Liquibase YAML changelog content'. The description adds context about supported change types but no additional semantic meaning for the parameter itself, so baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: analyzing Liquibase YAML changelogs for lock risks, data loss potential, and unsafe patterns. It lists specific supported change types and inline SQL checks, which distinguishes it from sibling tools like analyze_liquibase (likely for XML) or analyze_migration (broader scope).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The context is clear: use this tool when you have a Liquibase YAML changelog to analyze. However, it does not explicitly state when not to use it or suggest alternatives among sibling tools, so it misses some guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Analyze a SQL migration file for lock risks, data loss potential, and unsafe patterns. Detects: ACCESS EXCLUSIVE locks (DROP TABLE, ADD COLUMN NOT NULL, type changes, CREATE INDEX without CONCURRENTLY), data loss operations (TRUNCATE, DELETE without WHERE, UPDATE without WHERE, DROP COLUMN), and cascade risks. Supports Flyway versioned (V__*.sql) and repeatable (R__*.sql) migrations, as well as plain SQL files.
| Name | Required | Description | Default |
|---|---|---|---|
| sql | Yes | The SQL content of the migration file | |
| filename | Yes | Migration filename (e.g., V2__add_user_email.sql) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, description provides a detailed list of detection patterns (e.g., ACCESS EXCLUSIVE locks, data loss operations, cascade risks) but omits behavioral traits like processing limits, side effects (assumed read-only), or performance implications. Sufficient for basic understanding but could be more thorough.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is concise and front-loaded with the core purpose, then lists specific patterns in bullet-like format. Each sentence adds value; no fluff. Could be slightly more structured (e.g., spacing) but largely efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
As a static analysis tool without an output schema, the description should clarify what the tool returns (e.g., list of risks, severity scores). It currently lists what it detects but not the response format, leaving agents unsure of how to interpret output.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema has 100% description coverage for both parameters (filename, sql). Description adds context about filename patterns (V__*.sql, R__*.sql) beyond schema, but this is marginal. Baseline 3 is appropriate given high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it analyzes SQL migration files for lock risks, data loss, and unsafe patterns. Lists specific detectable operations (e.g., ACCESS EXCLUSIVE locks, data loss operations) and distinguishes from sibling tools (analyze_liquibase, analyze_liquibase_yaml) by specifying Flyway support.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states support for Flyway versioned and repeatable migrations, and plain SQL files, which guides when to use this tool. However, lacks explicit when-not-to-use or direct comparison to siblings, though naming and context provide implicit differentiation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Detect structural conflicts between two SQL migration files — same-table modifications, same-column changes, lock contention, and drop dependencies. Use this when two migrations touch the same schema objects and you need to know if ordering or concurrent execution matters. Note: only structural conflicts are detected (same table/column); semantic conflicts such as two migrations adding different indexes on the same column are not reported.
| Name | Required | Description | Default |
|---|---|---|---|
| sql_a | Yes | SQL content of the first migration | |
| sql_b | Yes | SQL content of the second migration | |
| filename_a | Yes | First migration filename (e.g., V3__add_email.sql) | |
| filename_b | Yes | Second migration filename (e.g., V4__modify_users.sql) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It explains what conflicts are detected (structural) and what are not (semantic), and mentions lock contention and drop dependencies. However, it does not describe output format or performance characteristics, leaving minor gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences: first defines purpose, second gives usage and limitation. No unnecessary words. Every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given sibling tools complexity and no output schema, the description is fairly complete. It specifies scope and limitations. However, it lacks any indication of what the tool returns, which would be helpful for a conflict detection tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description does not add new parameter meaning beyond the schema; it merely states the tool's purpose which implies the parameters are migration files. No additional syntax or format details are provided.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool detects structural conflicts between two SQL migration files, listing specific types (same-table, same-column, lock contention, drop dependencies). It differentiates from siblings like analyze_migration by focusing on conflict detection between two files.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says 'Use this when two migrations touch the same schema objects and you need to know if ordering or concurrent execution matters.' It also notes a limitation: semantic conflicts like different indexes are not reported, providing when-not-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generate reverse DDL to undo a SQL migration. Produces rollback SQL with warnings for irreversible operations (DROP TABLE, DROP COLUMN, type changes). Includes Flyway schema_history cleanup.
| Name | Required | Description | Default |
|---|---|---|---|
| sql | Yes | The SQL content of the migration file | |
| filename | Yes | Migration filename (e.g., V2__add_user_email.sql) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must fully disclose behavior. It mentions generating rollback SQL with warnings for irreversible operations and Flyway schema_history cleanup. However, it does not clarify execution side effects (e.g., does it apply changes or only produce text?) or authentication requirements, leaving some behavioral gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise at two sentences, with no filler. It is front-loaded with the primary action ('Generate reverse DDL') and then adds key details, making it easy for an agent to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Without an output schema, the description partially compensates by stating the tool produces rollback SQL with warnings and Flyway cleanup. However, it does not describe the format of the output or how warnings are presented, leaving some ambiguity for an agent expecting a structured response.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% coverage with descriptions for both 'filename' and 'sql'. The description adds no additional meaning beyond the schema examples (e.g., filename format is already illustrated). Thus, it meets the baseline for high schema coverage but does not compensate further.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Generate reverse DDL to undo a SQL migration.' It specifies the output (rollback SQL with warnings for irreversible operations) and mentions Flyway cleanup, distinguishing it from sibling analysis tools like analyze_migration and detect_conflicts.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when undoing a migration but does not explicitly state when to use this tool versus alternatives, nor does it provide 'when not to use' guidance. It lacks explicit comparison with sibling tools, leaving room for ambiguity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Calculate the combined risk score (0-100) for a SQL migration. Aggregates both lock risk severity (ACCESS EXCLUSIVE, SHARE locks) and data loss potential (DROP, TRUNCATE, type changes) into a single score. Useful for CI gates and automated migration review pipelines.
| Name | Required | Description | Default |
|---|---|---|---|
| sql | Yes | The SQL content of the migration file | |
| filename | Yes | Migration filename |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses that the tool aggregates lock risk and data loss potential into a score, but does not explicitly state that it is read-only or has no side effects. Since no annotations are provided, the description carries full burden; it is adequate but lacks explicit safety information.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences long, front-loading the purpose and output range in the first sentence, and elaborating on the components and use case in the second. No redundant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description explains the output (0-100 score) and what it comprises, which is sufficient for an agent to understand the return value. It could provide more detail on interpretation, but given the simplicity and no output schema, it is complete enough.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Both parameters (filename and sql) have descriptions in the input schema with 100% coverage. The tool description does not add further meaning to these parameters beyond what the schema provides, so baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool calculates a combined risk score (0-100) for SQL migrations, specifying the aggregated factors (lock risk severity and data loss potential). This distinguishes it from sibling tools like analyze_migration or detect_conflicts, which serve different purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions the tool is useful for CI gates and automated migration review pipelines, providing context on when to use it. However, it does not explicitly state when not to use it or mention alternatives, though sibling tools cover related but distinct tasks.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Each tool has a distinct purpose: analyze different input formats, score risk, generate rollback, and detect conflicts. No two tools overlap in functionality.
All tool names follow a consistent snake_case pattern with clear verb_noun structure (e.g., analyze_migration, generate_rollback), making them predictable for an agent.
With 6 tools, the server is well-scoped for a migration advisor. Each tool covers a necessary aspect without redundancy or excess.
The tools cover analysis, scoring, rollback generation, and conflict detection for SQL and Liquibase formats. A minor gap is the lack of a tool for overall migration order validation or automatic fixing, but the core advisory workflow is complete.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Scans schema metadata to classify PHI, score HIPAA readiness, and generate compliant migrations.
Deterministic safety, correctness & cost gate that vets Postgres SQL before your AI agent runs it.
Risk-scan a diff, flag AI-generated-code tells, find secrets. 5 of 7 tools need no account.
API governance for AI agents. Detects breaking changes, scores blast radius, blocks unsafe calls.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Dmitriusan/mcp-migration-advisor'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
