mcp-backend
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CATALOG_URI | No | Iceberg REST Catalog URI | |
| S3_ENDPOINT | No | S3-compatible endpoint URL | |
| BACKEND_MODE | No | Mode: 'supabase' (full) or 'postgres' (DB + S3 storage) | |
| POSTGRES_URL | No | PostgreSQL connection string | |
| SUPABASE_URL | No | Supabase project URL (required in supabase mode) | |
| ICEBERG_TOKEN | No | Bearer token for Iceberg catalog | |
| STORAGE_BUCKET | No | Default S3 bucket name (postgres mode) | |
| STORAGE_REGION | No | S3 region (default: us-east-1) | |
| AWS_ACCESS_KEY_ID | No | S3-compatible access key | |
| ICEBERG_NAMESPACE | No | Iceberg namespace (default: audit) | |
| ICEBERG_WAREHOUSE | No | Iceberg warehouse name | |
| SUPABASE_SECRET_KEY | No | Supabase service role key (supabase mode) | |
| STORAGE_ENDPOINT_URL | No | S3-compatible endpoint (required in postgres mode) | |
| AWS_SECRET_ACCESS_KEY | No | S3-compatible secret key | |
| STORAGE_ACCESS_KEY_ID | No | S3 access key (postgres mode) | |
| SUPABASE_PUBLISHABLE_KEY | No | Supabase anon/publishable key (supabase mode) | |
| STORAGE_SECRET_ACCESS_KEY | No | S3 secret key (postgres mode) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| run_base_seedA | Runs all SQL files in base/ (02-base equivalent with real natuleadan company data) |
| run_data_seedB | Runs all SQL files in data/ (03-data.ee equivalent with real users, products, courses) |
| run_all_seedsB | Runs base seed then data seed in order |
| list_seed_filesB | Lists all SQL files available in base/ and data/ |
| query_dbA | Run a raw SQL SELECT query against the database. READ ONLY - for inspection/verification. |
| list_tablesA | List all tables in the public schema |
| execute_sqlA | Run any SQL statement (INSERT, UPDATE, DELETE, SELECT, etc.) with full bypass of RLS. Use with care. |
| execute_rls_sqlA | Run a SELECT query impersonating a user role (applies RLS). Useful to test what a role can see. Only available in supabase mode. |
| list_bucketsA | List all Supabase storage buckets with their visibility |
| list_filesB | List files in a bucket folder |
| upload_fileB | Upload any local file to a storage bucket. local_path can be absolute (/Users/...) or relative to buckets/{bucket}/ |
| delete_fileB | Delete a file from a storage bucket |
| get_signed_urlB | Generate a signed URL for a private bucket file |
| get_public_urlA | Get the public URL for a file in a public bucket |
| download_bucketA | Download files from Supabase storage to local buckets/ folder. Can download all buckets, one bucket, a specific folder, or a single file. |
| list_iceberg_tablesA | List all foreign tables in the iceberg schema (mapped via FDW in Postgres) |
| query_icebergB | SELECT from an Iceberg foreign table via Postgres FDW (e.g. 'iceberg.aud_analytics_lake') |
| list_iceberg_catalog_tablesC | List tables directly from the Iceberg REST Catalog (requires CATALOG_URI + AWS credentials) |
| bootstrap_icebergA | Bootstrap the Iceberg FDW on Postgres: creates namespace + tables in catalog, configures FDW server, maps foreign tables, and verifies connection. |
| table_infoB | Describe table schema: columns, types, constraints, indexes |
| column_statsA | Get column statistics: cardinality, NULL count, data distribution |
| validate_sqlA | Parse SQL without executing - catch syntax errors early |
| query_with_explainA | Run query with EXPLAIN ANALYZE for performance debugging |
| active_queriesC | List active/long-running queries with details (duration, memory, locks) |
| database_statsC | Database statistics: table sizes, row counts, growth metrics |
| index_infoC | List indexes with size, scan count, and usage stats |
| bulk_upload_filesB | Upload multiple local files to storage with optional filtering by file type. Can upload individual files or an entire folder with selective file extensions. |
| call_rpcA | Call a Supabase PostgreSQL function (RPC) via the REST API. Uses service_role — bypasses RLS. |
| execute_sql_fileB | Execute SQL file content (PL/pgSQL blocks, multi-statement scripts). Pass raw SQL from file as string. |
| generate_and_update_signed_urlA | Generate a signed URL for a private bucket file and update the URL in a DB media table |
| manage_bucketB | Create, update, delete or empty a storage bucket. Works with Supabase Storage (supabase mode) or S3-compatible (postgres mode). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/nla-agent/mcp-backend'
If you have feedback or need assistance with the MCP directory API, please join our Discord server