Postgram for VS Code
io.github.ivo-toby/postgram
Self-hosted memory for AI agents with hybrid search, knowledge graphs, tasks, and document sync.
client:VS Code
transport:stdio
runtime:oci
Install Postgram in VS Code
.vscode/mcp.json
{
"inputs": [
{
"type": "promptString",
"id": "database-url",
"description": "DATABASE_URL",
"password": true
},
{
"type": "promptString",
"id": "openai-api-key",
"description": "OPENAI_API_KEY",
"password": true
},
{
"type": "promptString",
"id": "embedding-provider",
"description": "EMBEDDING_PROVIDER",
"password": true
},
{
"type": "promptString",
"id": "embedding-base-url",
"description": "EMBEDDING_BASE_URL",
"password": true
},
{
"type": "promptString",
"id": "admin-mfa-secret-key",
"description": "ADMIN_MFA_SECRET_KEY",
"password": true
},
{
"type": "promptString",
"id": "admin-settings-encryption-key",
"description": "ADMIN_SETTINGS_ENCRYPTION_KEY",
"password": true
}
],
"servers": {
"postgram": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/ivo-toby/postgram@sha256:29b61fb302bd52862b8eba43305ee2aa4fc072d5f9188652f1fe6324f49d5391"
],
"env": {
"DATABASE_URL": "${input:database-url}",
"OPENAI_API_KEY": "${input:openai-api-key}",
"EMBEDDING_PROVIDER": "${input:embedding-provider}",
"EMBEDDING_BASE_URL": "${input:embedding-base-url}",
"ADMIN_MFA_SECRET_KEY": "${input:admin-mfa-secret-key}",
"ADMIN_SETTINGS_ENCRYPTION_KEY": "${input:admin-settings-encryption-key}"
}
}
}
}
VS Code prompts for each input the first time the server starts, so no secret is written to the file. VS Code docs