Chroma’s official MCP server: vector search and collection management for RAG workflows.
Nothing to run from here
pgman 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.
91/100
trust score
11
tools declared
local
runs on your machine
—
calls last 7d
What it does
PostgreSQL for coding agents: schema, read-only queries, EXPLAIN, masked dumps, confirmed writes.
Quickstart
Install it the way its author documents:
1. cargo install pgman --version 0.5.1
The full guide: https://crates.io/crates/pgman
Publishernot claimed
TOAll 4 servers
tombaldwin4 servers
4 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 pgman 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.
Install it the way its author documents:
1. cargo install pgman --version 0.5.1
The full guide: https://crates.io/crates/pgman
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.
What this pgman MCP server is and what it will and won't do: the build, the client capabilities it saw, the write surface (apply_patches and restore, the tools that write to a database, after the operator confirms each run; dump, which writes a dump file in the working directory, likewise…
No parameter schema on file.
The named connections query accepts: each one's host, port, database and user, whether it opens an ssh tunnel, where its password comes from (never the password), where the definition came from, whether it is usable now and, if not, why, and which other entries reach the same database. Personal…
No parameter schema on file.
Run ONE SQL statement against a named connection and return its rows as JSON (SQL NULL as null, numbers and booleans unquoted). The session is read-only whatever pgman's safety.toml says (default_transaction_read_only=on), and the statement passes the same guard rails as pgman --batch; anything…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| connection | string | yes | A name from connections. |
| sql | string | yes | Exactly one statement. |
| max_rows | integer | no | Default 200. |
Pre-flight for a schema change: client sessions that have held a transaction open for at least min_xact_age_secs (default 60), are blocked, are blocking another session, or hold or wait for a lock on one of tables. Each session lists its locks on those tables (on any table when tables is…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| connection | string | yes | A name from connections. |
| tables | array | no | Tables the change will touch. |
| min_xact_age_secs | integer | no | Default 60. |
Which schema patch files the database has not recorded as applied. Reads every *.sql file in the patch directory, takes each file's id from its own version-row INSERT (INSERT INTO <table> (<column>, ...) VALUES (<id>, ...)), and compares that with the ids in <table>.<column>. Also reports recent…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| connection | string | yes | A name from connections. |
| dir | string | no | Patch directory, relative to the project root. |
| table | string | no | Version table, name or schema.name. |
| column | string | no | Id column in the version table. |
Every database in each configured environment, replicas included: server, role (primary, replica, direct), which primary a replica follows, endpoint, engine version, instance status (e.g. stopped), class and multi-AZ. Environments come from environments.toml in pgman's config dir. An rds source…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| probe | boolean | no | Connect to the databases of environments that opted into probes. Default false. |
The schema wizard's findings for one connection: tables without a primary key or unique constraint, mixed-case identifiers, and the live checks — foreign keys without a supporting index, unused indexes, overlapping indexes, table bloat, tables without a comment, schemas mixing timestamp with and…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| connection | string | yes | A name from connections. |
Recent errors from an RDS server's Postgres log: ERROR, FATAL and PANIC lines from its newest log files, grouped by message with a count, the user@database that last hit it, and when. The server must be one an rds environment in environments.toml lists (see environments). CAVEATS: reads…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| environment | string | yes | — |
| server | string | yes | An RDS instance identifier the environment lists. |
| files | integer | no | Newest log files to read. Default 6. |
Apply an environment database's pending schema patches, after the OPERATOR confirms through an elicitation prompt (a protected environment — protected = true, or a name containing "prod" — by typing its name). Plans first, read-only: the pending patches in order, each checked against…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| environment | string | yes | — |
| server | string | yes | — |
| database | string | yes | — |
| mode | string | no | — |
Propose environments from an AWS account, for environments.toml: one per RDS Postgres primary with its read replicas, the Secrets Manager secret matching each database by NAME, the bastion (public EC2 host) in the instance's VPC, sslmode=require, the account and region pinned. Each proposal has…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| region | string | no | — |
| profile | string | no | — |
| account | string | no | Refuse unless the AWS credentials belong to this account. |
Append the named proposals from a fresh environments_discover to environments.toml in pgman's config dir. Only what discovery proposes can be saved — names choose among proposals, nothing else is written — and the file's existing content is never rewritten; the result must load or nothing is…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| names | array | yes | Proposal names from environments_discover. |
| region | string | no | — |
| profile | string | no | — |
| account | string | no | — |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under Apache-2.0
- 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 pgman 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 91 / 100
Release 0.5.1 · scanned 10 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 score91
Findings1 threat · 0 capability
Capabilityminimal
Coveragemetadata
Verificationrepo
Surface digest2dc22d3bf39daa3966da07121ef3ae7218597d0cc75600bd6ac9471b4c82a657
Score vectorthreat 100 → client 91
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | metadata | inspection depth (metadata) — how much of the target the scan could see | −8 |
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 surfacenot available
Implementation sourcenot available
Package metadataread
Live transportnot available
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
The implementation source was not read — the published package was fetched but contains no source files the scanner reads.
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. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
No tool surface was enumerated, so there is nothing to attribute a capability to.
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 digest2dc22d3bf39daa39
Scanned2026-11-10
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
It installs from its repository rather than from a versioned package, so the command cannot be pinned to a release. The history below is for reading; the current release on file is 0.5.1.
0.5.1
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 pgman 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.