chat-sql (Umair444/chat-sql-mcp) is an MCP server listed on the M8ven Trust Index. It scores 73 out of 100, grade C. It declares 32 tools. No publisher has claimed this listing.

Caution

73/100

chat-sql

Item: chat-sql
Rating: 73
Author: M8ven

MCP server that enables natural-language SQL queries across multiple databases (ClickHouse, Teradata, PostgreSQL, MySQL, SQL Server, DB2, Oracle, MongoDB) with dialect-correct SQL generation, PII masking, and security-by-construction controls.

→ Umair444/chat-sql-mcp · listed on glama

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every push why connect →

Who stands behind it

Umair444

Source: Glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

Glamanot scored here

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings

✅

No credential exfiltration, no sensitive file access, no obfuscation

Static analysis found nothing flowing your secrets to unexpected places.

✅

Open source with a license and README

Anyone can audit the code, the license is declared, and the publisher documents what it does.

🔐

You'll be asked for 2 credentials: CHATSQL_BROKER_TOKEN, CHATSQL_CONNECTOR_TOKEN

These are read from process.env at runtime. Make sure you trust where they’ll be sent.

// tools this server exposes32 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

run_query

Execute SQL on a configured database and return a PII-masked markdown table.

run_query_file

Execute SQL read from a .sql file. Same governance as run_query.

export_to_csv

Stream a SELECT's results to a CSV file. The raw values are written to the file but NEVER returned to you — you receive only the row count and path. This is the sanctioned path for identifier-level exports (e.g. lead lists).

load_file

Bulk-load a local file (CSV/Excel/Parquet/ODS/JSON/XML) into a tmp_ scratch table. The table is recorded as assistant-owned, so you may later query, write to, or drop it. Call drop_table when done.

drop_table

Drop a tmp_ scratch table you created. Refused for any other table.

list_databases

List configured databases (short code, alias, service). No credentials shown.

explain_query

Return the database's query plan (EXPLAIN) without executing the query.

search_schema

Search the documented schema files (schemas/*.md) for a keyword — table or column names, business notes. Reads local docs only, never the database.

table_info

Show a documented table's section from schemas/*.md (columns, notes).

long_running_queries

List active PostgreSQL queries running longer than min_seconds (read-only).

kill_query

Cancel (or with force=True, terminate) a PostgreSQL backend by pid.

find_similar_queries

Retrieve past NL→SQL examples similar to `question` for style/reuse.

save_query_example

Save a verified, reusable NL→SQL example to the RAG store.

delete_query_example

Delete a RAG example by id.

run_python

Execute Python for LOCAL data transformation (pandas/openpyxl/pyarrow/…).

whatsapp_send_text

Send a WhatsApp text to a JID (person or group).

whatsapp_presence

Set chat presence ('typing' or 'paused').

whatsapp_send_file

Send a local file to a WhatsApp JID.

whatsapp_read_messages

Read recent messages from a chat/group JID.

whatsapp_search_contacts

Search WhatsApp contacts and groups by name; returns JIDs.

whatsapp_forward_message

Forward an existing WhatsApp message (reuses uploaded media).

whatsapp_download_media

Download a message's media; returns the local file path.

transcribe_audio

Download a WhatsApp voice note and transcribe it locally with Whisper.

send_email

Send an email via the configured SMTP relay (config.py / .env).

notify

Append a line to logs/notify.log (a simple local notification sink).

wiki_read

Read a wiki/memory markdown page by name from CHATSQL_WIKI_DIR.

wiki_search

Grep wiki pages for a query string.

wiki_write

Write (or append to) a wiki/memory markdown page.

jupyter_run

Run Python on a remote Jupyter kernel (persistent across calls).

jupyter_run_file

Run a local .py file's contents on the remote Jupyter kernel.

jupyter_kernel_status

Report the remote Jupyter kernel status.

jupyter_restart_kernel

Restart the remote Jupyter kernel (clears in-memory state).

// environment variables

To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.

configCHATSQL_PII_SALT

configCHATSQL_RAG_DBKEYdelete_query_example (needs a pgvector DB; set ).

configCHATSQL_HOME

configCHATSQL_WHATSAPP_ENABLED

configCHATSQL_EMAIL_ENABLED

configCHATSQL_JUPYTER_ENABLED

configCHATSQL_WIKI_ENABLED

configCHATSQL_DB_CREDS

configCHATSQL_GATEWAY_SOCKET

configCHATSQL_PII_POLICY

configCHATSQL_LEDGER

configCHATSQL_AUDIT_LOG

🔐 secretCHATSQL_BROKER_TOKEN

configCHATSQL_TD_SCRATCH

🔐 secretCHATSQL_CONNECTOR_TOKEN

// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

32/32 tools missing one or more hints — run_query (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); run_query_file (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); export_to_csv (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +29 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Destructive tools are labelled

1 tool perform destructive updates without destructiveHint — run_python deletes at line 439 (shutil.rmtree(workdir, ignore_errors=True))

Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.

Tool test coverage

Only 1/32 tools referenced in tests (3%)

Write tests that reference each tool by name so every tool has at least one test.

Secrets never reach shell commands

1 secret value passed to a subprocess as an argument — no shell is invoked, so there is nothing to inject into

Never pass secrets through shell commands. Use library APIs that accept credentials as arguments.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail

The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.

// improvement guidance — verified publishers only

We have 5 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.

// embed badge in your README

[![M8ven Verified](https://m8ven.ai/badge/mcp/umair444/chat-sql-mcp?variant=verified)](https://m8ven.ai/mcp/umair444/chat-sql-mcp)

Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.

commit: ac109a8348d8705c14746ecc96391b1937647251

code hash: 477e32631b548e0a9f492496b6c05867814a2bc87699c1d10072a11b2d4de708

view raw JSON →

Check MCPs from inside your assistant

Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check

check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern

How to add it →Free · no account needed · works in any MCP client