Live survey286 models · 13 providers · 19,992 auditsAudited verification-before-completion · SAFE →What changedHow we verifyllms.txt

MCP server · Org-owned · Audited from source

Whodb MCP server

by clidey/whodbApache-2.0 licenceAudited 21 Sep 2026 · source 4f4b840f0079

npm @clidey/whodb-sdkstreamable-http★ 5,033
✕BLOCKGrade F · 24/100 · 21 Sep 2026 · 4f4b840
Safer alternativesView source on GitHub ↗

Is it safe? No — BLOCK, grade F (24/100). It exposes 4 tools: 4 read, 0 write and 0 destructive. The audit recorded 69 findings (3 critical, 14 high, 17 medium, 35 low). Maintainer's description: Where data access meets operational intelligence

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
CoCopilotAIGoogle AI Mode
Cite

Cite this page

ModelsAtlas. “Whodb MCP server (clidey/whodb)”. Retrieved 21 Sep 2026. https://modelsatlas.com/mcp/clidey/whodb

Why this is BLOCK. The audit found 3 critical and 14 high findings; the most severe is Hard-coded secrets at dev/certs/ca/clickhouse/ca-key.pem:1. Each finding is listed below with its file and line.

Why this page is still public. People search for this server by name. Hiding it would leave them with the README's word alone; here they see what the code does. We list it so you can decide, and we do not show connect commands for BLOCK servers.

Trust audit

Audit 0.4.1 · full source read 21 Sep 2026

Trust score24/100✕BLOCK F
3 critical14 high17 medium35 low0 info

69 findings, listed below with the file and line each was found on. Grade A needs a sandboxed behavioural run too; this audit read the source only.

What the source does

  • FilesystemDeclared15 observations
  • NetworkDeclared10 observations
  • ShellDeclared10 observations
  • DependenciesPinnedNothing floats
  • SecretsFoundSee the findings

Findings (69)

Sorted by severity · the 25 most severe of 69 are listed

CRITICALHard-coded secretssecret.private_key · dev/certs/ca/clickhouse/ca-key.pem:1
F-03 Hard-coded secretsCWE-798 · CWE-321Layer L1

Excerpt withheld: it is a secret, and we never print one.

Why
No further detail recorded for this rule.
Fix
—
CRITICALHard-coded secretssecret.private_key · dev/certs/ca/cockroachdb/ca-key.pem:1
F-03 Hard-coded secretsCWE-798 · CWE-321Layer L1

Excerpt withheld: it is a secret, and we never print one.

Why
No further detail recorded for this rule.
Fix
—
CRITICALHard-coded secretssecret.private_key · dev/certs/ca/elasticsearch/ca-key.pem:1
F-03 Hard-coded secretsCWE-798 · CWE-321Layer L1

Excerpt withheld: it is a secret, and we never print one.

Why
No further detail recorded for this rule.
Fix
—
HIGHCode injectioncode.eval_exec · core/graph/generated.go:3355
F-02 Code injectionCWE-78 · CWE-94 · CWE-95Layer L1
func (e *executableSchema) Exec(ctx context.Context) graphql.ResponseHandler {
Why
evaluates text as code
Fix
remove; use a parser or a dispatch table
HIGHCode injectioncode.eval_exec · sdk/packages/go/auth.go:62
F-02 Code injectionCWE-78 · CWE-94 · CWE-95Layer L1
func (c *cliCredentials) exec(ctx context.Context) (*printTokenOutput, error) {
Why
evaluates text as code
Fix
remove; use a parser or a dispatch table
HIGHCode injectioncode.eval_exec · sdk/packages/rust/src/auth.rs:60
F-02 Code injectionCWE-78 · CWE-94 · CWE-95Layer L1
fn exec(&self) -> Result<CliCache> {
Why
evaluates text as code
Fix
remove; use a parser or a dispatch table
HIGHCode injectioncode.eval_exec · sdk/packages/typescript/src/auth.ts:86
F-02 Code injectionCWE-78 · CWE-94 · CWE-95Layer L1
cached = await exec();
Why
evaluates text as code
Fix
remove; use a parser or a dispatch table
HIGHCode injectioncode.eval_exec · sdk/packages/typescript/src/auth.ts:94
F-02 Code injectionCWE-78 · CWE-94 · CWE-95Layer L1
if (!cached) cached = await exec();
Why
evaluates text as code
Fix
remove; use a parser or a dispatch table
HIGHFilesystem / pathfs.credential_store · .agents/skills/impeccable/scripts/hook-lib.mjs:81
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
String.raw`(?:^|[/\\])id_rsa(?:$|[._-])[^/\\]*$`,
Why
touches a credential store
Fix
—
HIGHFilesystem / pathfs.credential_store · cli/cmd/guide.go:272
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
Requires the host to be in your ~/.ssh/known_hosts file.
Why
touches a credential store
Fix
—
HIGHFilesystem / pathfs.credential_store · cli/internal/ssh/tunnel.go:178
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
return nil, fmt.Errorf("~/.ssh/known_hosts not found — run 'ssh %s' once to add the host key", "user@host")
Why
touches a credential store
Fix
—
HIGHFilesystem / pathfs.credential_store · cli/internal/tui/connection_view.go:248
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
inputs[fieldSSHKeyFile] = newInput("~/.ssh/id_rsa", 200)
Why
touches a credential store
Fix
—
HIGHFilesystem / pathfs.credential_store · frontend/src/locales/components/aws-connection-picker.yaml:14
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
helpAuthDefaultDesc: uses ~/.aws/credentials, env vars, or IAM role
Why
touches a credential store
Fix
—
HIGHNetwork egressnet.metadata_ip · core/src/security/egress.go:106
F-04 Network egressCWE-200 · CWE-319Layer L1
if ip.Equal(net.ParseIP("169.254.169.254")) {
Why
cloud metadata endpoint: the classic SSRF credential grab
Fix
—
HIGHNetwork egressnet.tls_off · dev/docker-compose.yml:123
F-04 Network egressCWE-200 · CWE-319Layer L1
- --insecure
Why
certificate verification is disabled
Fix
leave verification on
HIGHNetwork egressnet.tls_off · dev/sample-data/cockroachdb/init.sh:35
F-04 Network egressCWE-200 · CWE-319Layer L1
CONN_FLAGS="--insecure"
Why
certificate verification is disabled
Fix
leave verification on
HIGHPrompt injectionprompt.hide_from_user · .agents/skills/impeccable/reference/critique.md:229
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
This is fire-and-forget. Do not show the user the helper's JSON output; only the human-readable trend line and the written path. Failures here should not block the rest of the flow; print the error an
Why
asks the agent to act without the user's knowledge
Fix
—
MEDIUMInventory / provenanceinv.binary · dev/sample-import-data/clickhouse/data_types.xlsx
F-13 Inventory / provenanceCWE-1104Layer L0
data_types.xlsx
Why
a compiled or binary member cannot be reviewed from source
Fix
ship source, or explain the binary in the README
MEDIUMInventory / provenanceinv.binary · dev/sample-import-data/clickhouse/orders.xlsx
F-13 Inventory / provenanceCWE-1104Layer L0
orders.xlsx
Why
a compiled or binary member cannot be reviewed from source
Fix
ship source, or explain the binary in the README
MEDIUMInventory / provenanceinv.binary · dev/sample-import-data/clickhouse/products.xlsx
F-13 Inventory / provenanceCWE-1104Layer L0
products.xlsx
Why
a compiled or binary member cannot be reviewed from source
Fix
ship source, or explain the binary in the README
MEDIUMInventory / provenanceinv.binary · dev/sample-import-data/cockroachdb/data_types.xlsx
F-13 Inventory / provenanceCWE-1104Layer L0
data_types.xlsx
Why
a compiled or binary member cannot be reviewed from source
Fix
ship source, or explain the binary in the README
MEDIUMInventory / provenanceinv.binary · dev/sample-import-data/cockroachdb/orders.xlsx
F-13 Inventory / provenanceCWE-1104Layer L0
orders.xlsx
Why
a compiled or binary member cannot be reviewed from source
Fix
ship source, or explain the binary in the README
MEDIUMInformation disclosuredisclose.log_secret · .agents/skills/impeccable/scripts/live-server.mjs:1662
F-12 Information disclosureCWE-209 · CWE-532Layer L1
console.log(`Token: ${state.token}\n`);
Why
No further detail recorded for this rule.
Fix
—
MEDIUMNetwork egressnet.beacon_words · .agents/skills/impeccable/scripts/palette.mjs:290
F-04 Network egressCWE-200 · CWE-319Layer L1
strategy: "Pure near-black bg lets the seed's cold marine blue read as a luminous beacon, while a pale frost-cyan accent evokes diffused dawn light cutting through fog." },
Why
No further detail recorded for this rule.
Fix
—

Tools it exposes

4 declared in source · 0 destructive

4 read0 write0 destructive
ToolWhat it doesRisk
HeadphonesNoise-canceling headphonesread
LaptopHigh-performance laptopread
Monitor4K UHD Monitorread
SmartphoneLatest model smartphoneread

Safer alternatives

lambda-data-pipeline-mcp✓SAFE

SEOSiri-Official/lambda-data-pipeline-mcp

A sovereign, high-speed, local-first Big Data Ingestion, Filtering, and Analytical Pipeline Orchestrator over the Model Context Protocol.

7 readGrade B
tdries-tableau-graphql✓SAFE

tdries/tableau-graphQL-mcp

Read-only MCP server for Tableau lineage and impact analysis over the Metadata API (GraphQL). Works on Tableau Server and Cloud.

1 writeGrade B

Audit history

  1. ✕BLOCK F 24 / 100

    Source changed, verdict held · 4f4b840f0079

  2. ✕BLOCK F 24 / 100

    First audit · 660016fbed80

README badge

Badges show the current verdict, BLOCK included

ModelsAtlas: BLOCK FMODELSATLASBLOCK · F

A badge cannot be hidden by the maintainer while the verdict is BLOCK. Fix the findings, push, and the re-audit updates it.

Questions about Whodb MCP server

What is the Whodb MCP server?
Where data access meets operational intelligence
What tools does Whodb expose?
4 in total: 4 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Whodb safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (24/100) and found 17 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does Whodb need?
It reads OPENAI_API_KEY, WHODB_API_KEY and WHODB_IPC_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Whodb run?
It speaks streamable-http, so it runs as a service you connect to over the network. It is published on npm as @clidey/whodb-sdk at 0.0.0.
How current is this page?
The grade is for one exact copy of the source (4f4b840f0079), read on 2026-09-21. The repository is watched and re-audited when it changes.
I already installed Whodb. What should I do?
Remove it from your client's MCP configuration, then rotate any API keys and tokens that were in your environment while it ran.
Can the verdict change?
Yes. The repository is watched and re-audited when its source changes. If the findings are removed the verdict updates, and the history on this page shows it.

Sources

  • clidey/whodb on GitHub — the source we read, its licence, stars and activityObserved · 21 Sep 2026
  • ModelsAtlas trust audit — BLOCK verdict for commit 4f4b840f0079Observed · 21 Sep 2026

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.