Chroma’s official MCP server: vector search and collection management for RAG workflows.
Nothing to run from here
Pgcloud is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
96/100
trust score
10
downloads a day
local
runs on your machine
298
downloads in 30d
What it does
Neon Postgres projects, branches, SQL, and migrations from your MCP client.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user pgcloud-mcp '--' npx -y @reneturcios/pgcloud mcp
# 2 — ask your agent for something these tools do
# list_projects, describe_project, create_project and 17 more
Pgcloud costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
CLAll 393 servers
CloudCorpRecords393 servers
28 categories
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Pgcloud as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user pgcloud-mcp '--' npx -y @reneturcios/pgcloud mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
20 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
List all Neon projects in your account.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | number | no | Maximum number of Neon projects to return. |
| search | string | no | Optional search term to filter projects by name. |
| org_id | string | no | Optional Neon organization ID; when given, only projects belonging to that organization are listed. |
Describes a Neon project
| Parameter | Type | Required | Notes |
|---|---|---|---|
| projectId | string | yes | ID of the Neon project to describe. |
Create a new Neon project.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | no | Optional name for the new Neon project; when omitted, Neon assigns a default name. |
| region_id | string | no | Optional Neon region ID in which to create the project, such as aws-us-east-1. |
| org_id | string | no | Optional Neon organization ID that will own the new project. |
Delete a Neon project
| Parameter | Type | Required | Notes |
|---|---|---|---|
| projectId | string | yes | ID of the Neon project to delete, together with everything in it. |
Create a branch in a Neon project
| Parameter | Type | Required | Notes |
|---|---|---|---|
| projectId | string | yes | ID of the Neon project in which to create the branch. |
| branchName | string | no | Optional name for the new branch; when omitted, Neon assigns a default name. |
| parentBranchId | string | no | Optional ID of the branch to copy from; when omitted, the branch is created from the project's default branch. |
Delete a branch from a Neon project
| Parameter | Type | Required | Notes |
|---|---|---|---|
| projectId | string | yes | ID of the Neon project that owns the branch. |
| branchId | string | yes | ID of the branch to delete. |
Get a tree view of all objects in a branch, including databases, schemas, tables, views, and functions
| Parameter | Type | Required | Notes |
|---|---|---|---|
| projectId | string | yes | ID of the Neon project that owns the branch. |
| branchId | string | yes | ID of the branch to describe, including the databases it holds. |
List compute endpoints for a project or a specific branch, including compute ID, type, and size.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| projectId | string | yes | ID of the Neon project whose compute endpoints to list. |
| branchId | string | no | Optional ID of a branch; when given, only compute endpoints for that branch are listed. |
List all organizations that the current user has access to, optionally filtered by a search term.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| search | string | no | Optional search term to filter organizations by name. |
Get a PostgreSQL connection string for a Neon database with all parameters being optional
| Parameter | Type | Required | Notes |
|---|---|---|---|
| projectId | string | yes | ID of the Neon project whose connection string to return. |
| branchId | string | no | Optional ID of the branch to connect to; when omitted, the project's default branch is used. |
| databaseName | string | no | Optional name of the database to connect to; when omitted, the project's default database is used. |
| roleName | string | no | Optional name of the database role to connect as; when omitted, the default role is used. |
| pooled | boolean | no | Optional flag: when true, return a pooled connection string (through Neon's connection pooler); when false or omitted, return a direct connection string. |
Execute a single SQL statement against a Neon database.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sql | string | yes | The single SQL statement to execute against the Neon database. |
| projectId | string | yes | ID of the Neon project that owns the database. |
| branchId | string | no | Optional ID of the branch to run against; when omitted, the project's default branch is used. |
| databaseName | string | no | Optional name of the database to run against; when omitted, the project's default database is used. |
| roleName | string | no | Optional name of the database role to run as; when omitted, the default role is used. |
Execute a SQL transaction against a Neon database, should be used for multiple SQL statements.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sql | array | yes | Array of SQL statements to execute together in a single transaction against the Neon database. |
| projectId | string | yes | ID of the Neon project that owns the database. |
| branchId | string | no | Optional ID of the branch to run against; when omitted, the project's default branch is used. |
| databaseName | string | no | Optional name of the database to run against; when omitted, the project's default database is used. |
| roleName | string | no | Optional name of the database role to run as; when omitted, the default role is used. |
Get all tables in a Neon database
| Parameter | Type | Required | Notes |
|---|---|---|---|
| projectId | string | yes | ID of the Neon project that owns the database. |
| branchId | string | no | Optional ID of the branch whose tables to list; when omitted, the project's default branch is used. |
| databaseName | string | no | Optional name of the database whose tables to list; when omitted, the project's default database is used. |
Describe the schema of a table in a Neon database
| Parameter | Type | Required | Notes |
|---|---|---|---|
| projectId | string | yes | ID of the Neon project that owns the table. |
| tableName | string | yes | Name of the table whose columns to describe. |
| branchId | string | no | Optional ID of the branch containing the table; when omitted, the project's default branch is used. |
| databaseName | string | no | Optional name of the database containing the table; when omitted, the project's default database is used. |
List slow queries from pg_stat_statements, ordered by mean execution time.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| projectId | string | yes | ID of the Neon project that owns the database. |
| branchId | string | no | Optional ID of the branch to inspect; when omitted, the project's default branch is used. |
| databaseName | string | no | Optional name of the database to inspect; when omitted, the project's default database is used. |
| limit | number | no | Optional maximum number of slow queries to return, clamped to between 1 and 100; defaults to 10. |
Describe the PostgreSQL query execution plan for a SQL statement by running EXPLAIN in the database
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sql | string | yes | The SQL statement whose PostgreSQL execution plan to return, run under EXPLAIN (ANALYZE, BUFFERS, FORMAT JSON). |
| projectId | string | yes | ID of the Neon project that owns the database. |
| branchId | string | no | Optional ID of the branch to explain against; when omitted, the project's default branch is used. |
| databaseName | string | no | Optional name of the database to explain against; when omitted, the project's default database is used. |
Perform a database schema migration by executing the given SQL on a temporary branch for safety, ready to complete onto the main branch.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| migrationSql | string | yes | The migration SQL to test on a temporary branch before it is applied to the original branch. |
| projectId | string | yes | ID of the Neon project that owns the database to migrate. |
| databaseName | string | no | Optional name of the database to migrate; when omitted, the project's default database is used. |
| branchId | string | no | Optional ID of the branch to migrate; the temporary branch is created from it and completion applies the migration back to it. When omitted, the project's default branch is used. |
Complete a database migration when the user confirms the migration is ready to be applied to the main branch.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| migrationId | string | yes | ID of the prepared migration session returned by prepare_database_migration. |
| projectId | string | yes | ID of the Neon project the migration was prepared for; must match the prepared migration's project. |
| databaseName | string | no | Optional name of the database to apply the migration to; when omitted, the database recorded when the migration was prepared is used. |
Analyze a slow query or DML statement on a temporary branch, returning its execution plan to suggest optimizations.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sql | string | yes | The slow query or DML statement to analyze on a temporary branch; its execution plan is returned to suggest optimizations. |
| projectId | string | yes | ID of the Neon project that owns the database. |
| databaseName | string | no | Optional name of the database the statement runs against; when omitted, the project's default database is used. |
| branchId | string | no | Optional ID of the branch to tune against; the temporary tuning branch is created from it. When omitted, the project's default branch is used. |
Complete a query tuning session by either applying the changes to the main branch or discarding them.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tuningId | string | yes | ID of the query tuning session returned by prepare_query_tuning. |
| projectId | string | yes | ID of the Neon project the tuning session was prepared for; must match the session's project. |
| applyChanges | boolean | yes | Whether to apply the tuning session's changes to the original branch (true) or discard them (false); the temporary branch is deleted either way. |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Pgcloud or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 96 / 100
Release 0.1.0 · scanned 2 Nov 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score96
Findings0 threat · 0 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digest999290ab44ffc9d71624e215cb04d539ae24ac670d1f312c21d3bf6e67671448
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (20 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| list_projects | no tags | |
| describe_project | no tags | |
| create_project | no tags | |
| delete_project | no tags | |
| create_branch | no tags | |
| delete_branch | no tags | |
| describe_branch | no tags | |
| list_branch_computes | no tags | |
| list_organizations | no tags | |
| get_connection_string | no tags | |
| run_sql | sensitive-source | sensitive-source: keyword "run_sql", parameter "sql" |
| run_sql_transaction | sensitive-source | sensitive-source: keyword "run_sql", parameter "sql" |
| get_database_tables | no tags | |
| describe_table_schema | no tags | |
| list_slow_queries | no tags | |
| explain_sql_statement | sensitive-source | sensitive-source: keyword "sql_query", parameter "sql" |
| prepare_database_migration | no tags | |
| complete_database_migration | no tags | |
| prepare_query_tuning | sensitive-source | sensitive-source: parameter "sql" |
| complete_query_tuning | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest999290ab44ffc9d7
Scanned2026-11-02
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.1.0. Pin a release below and the command asks for exactly that one.
0.1.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Pgcloud can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.