Finance Toolkit
500+ transparent financial methods calculated from raw statements, not third-party endpoints.
Description from the maker (original English)
Local, evidence-based application security assessment with an evidence ledger and retests.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Download the maker’s .mcpb file
The link goes to the maker’s own file; we do not host or repackage it. Open the file and Claude Desktop installs it.
Run this in your terminal
Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 8, 2026
The registry name was verified with the GitHub account ratomirjovanovic, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.2.13) reached the registry 3 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need MCPB on your computer.
In the same category: Finance Toolkit, SolidInvoice, Korea Tax Calculator
Servers in the same category from other makers, sorted by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
500+ transparent financial methods calculated from raw statements, not third-party endpoints.
Create and send invoices and quotes, manage clients, and track payments in SolidInvoice.
Korean tax calculation and tax-audit judgment MCP: 96 tools with statutory citations.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
PandaWard
Local, evidence-based application security assessment for your own code.
A standalone Go CLI and a Claude Code plugin. Passive by default. Honest about what it did not test.
Website and demo · Documentation · Quick start · Limitations
Most scanners print a list of alerts and stop. PandaWard keeps a ledger: every control it could check, how it checked it, the redacted evidence, and every control it could *not* decide. Findings are fingerprinted across runs, so a fix becomes REMEDIATED only when the check runs again and no longer sees the problem, and a moved or renamed file keeps its findings, their IDs and your triage instead of reading as fixed.
A real session on the bundled demo project, generated by tools/termdemo .
Findings from a real scan of the bundled vulnerable fixture. Open the live demo for the terminal replay and the full report.
| Safe by default | The default profile only reads the repository. It never runs install scripts, Makefiles or builds, never follows symlinks, and sends no traffic to any target. |
| Human-authorized network tests | Anything that sends a request needs a scope manifest that a person filled in and approved from an interactive terminal. An AI agent cannot approve it. |
| No false "all clear" | Only PASS and FAIL are decisive. A missing scanner is BLOCKED, a crash is ERROR, a heuristic hit is SUSPECTED. None of them count as secure. |
| Evidence, not opinions | Each finding links to a redacted, SHA-256 addressed evidence record. Model-proposed issues stay HYPOTHESIS until a human decides. |
| Secrets never leak | Values are masked before they are stored, printed, reported or returned to a model. .env and key files are recorded by name only. |
| Remembers across sessions | State lives in a local SQLite ledger, so context compaction or a restart does not lose results. |
| Cross-domain thinking | Links such as *identity -> authorization* (BC1) or *webhook -> payment state* (FG1) are created from shared assets in your code and tracked separately. |
| Private | No account and no cloud backend. Usage telemetry is off unless you turn it on yourself, and pandaward telemetry show prints every byte it would send (details). |
Formerly PenSec. The project was renamed to PandaWard in 0.2.0. If you used PenSec, see Moving from PenSec.
/plugin marketplace add ratomirjovanovic/pandaward
/plugin install pandaward@pandaward # macOS and Linux /plugin install pandaward-windows@pandaward # Windows
You can also run the same steps from a terminal with claude plugin marketplace add ratomirjovanovic/pandaward and claude plugin install pandaward-windows@pandaward (pandaward@pandaward on macOS and Linux). Restart Claude Code afterwards; /mcp should list plugin:pandaward:pandaward as connected. Install only one of the two plugins. If something goes wrong, see Troubleshooting.
Updating. Claude Code does not update third-party marketplaces on its own unless you turn it on. Either turn on auto-update once (/plugin, then Marketplaces, pandaward, Enable auto-update), or update by hand:
claude plugin marketplace update pandaward
claude plugin update pandaward-windows@pandaward # or pandaward@pandaward on macOS and Linux
Then restart Claude Code. /plugin shows the installed version.
Uninstalling. claude plugin uninstall pandaward-windows@pandaward (or pandaward@pandaward), then claude plugin marketplace remove pandaward. Results stay in each project's .pandaward/ directory until you delete it. The uninstall guide covers the CLI packages and every file PandaWard creates.
Then, in your project, ask Claude to check its security, or run:
/pandaward:start
That is the only command. Claude scans the project, has specialist reviewers look at what automation could not decide, triages the results, builds the fix plan and writes the reports, with a live checklist. At the end it asks one question - fix the plan, record the triage results, install missing scanners - and does what you choose, retesting after every fix. Later in the session it retests on its own whenever code changes. Commands that change a finding's status still show you a confirmation prompt, and network tests always need a scope you approve in your own terminal.
Individual skills
| Skill | What it does |
|---|---|
/pandaward:init | Create .pandaward/ and show what was detected |
/pandaward:scan | Passive scan with an honest summary |
/pandaward:review | Read-only specialist agents look at what automation could not decide |
/pandaward:fix-plan | Ordered fixes, applied one by one after your approval |
/pandaward:retest | Re-scan after changes and show the delta |
/pandaward:report | HTML, Markdown, JSON, SARIF, CSV |
/pandaward:status | Where the assessment stands and what is stale |
The plugin installs prebuilt, checksum-verified binaries from the
pluginandplugin-windowsbranches, which the release workflow publishes on every version tag (how to verify them). To use PandaWard without Claude Code, see below.
With a package manager:
brew tap ratomirjovanovic/pandaward https://github.com/ratomirjovanovic/pandaward && brew install ratomirjovanovic/pandaward/pandaward # macOS, Linux
scoop bucket add pandaward https://github.com/ratomirjovanovic/pandaward; scoop install pandaward/pandaward # Windows
Or download a binary from the releases page (Linux and macOS on amd64 and arm64, Windows on amd64). For example on Linux:
v=v0.2.13
curl -fLO https://github.com/ratomirjovanovic/pandaward/releases/download/$v/pandaward-linux-amd64 curl -fLO https://github.com/ratomirjovanovic/pandaward/releases/download/$v/SHA256SUMS sha256sum --ignore-missing -c SHA256SUMS chmod +x pandaward-linux-amd64 && sudo mv pandaward-linux-amd64 /usr/local/bin/pandaward
On Windows (PowerShell), save pandaward-windows-amd64.exe as pandaward.exe in a folder on your PATH:
Invoke-WebRequest https://github.com/ratomirjovanovic/pandaward/releases/download/v0.2.13/pandaward-windows-amd64.exe -OutFile pandaward.exe
(Get-FileHash pandaward.exe).Hash # compare with the line in SHA256SUMS
Or install with Go 1.26 or later: go install github.com/ratomirjovanovic/pandaward/cmd/pandaward@latest. The binary has no runtime dependencies.
Update with brew upgrade pandaward or scoop update pandaward; for a downloaded binary, replace the file with the new release. Remove with brew uninstall pandaward or scoop uninstall pandaward, or delete the binary. pandaward version shows what you have.
Then, in your project:
pandaward assess # init, scan with progress, reports and a summary
pandaward findings # then dig in pandaward fix-plan
Release binaries are reproducible and come with checksums, a CycloneDX SBOM and signed build provenance; docs/VERIFYING.md shows how to check them.
flowchart LR
subgraph Claude Code S[Skills /pandaward:*] --> M[MCP server] A[Read-only agents] --> M H[Hooks] --> L end CLI[pandaward CLI] --> E M --> E[Engine] E --> I[Inventory read-only walk] E --> AD[Adapters built-in + optional tools] E --> P[Scope and policy fail closed] AD --> R[Redaction] R --> EV[Evidence store SHA-256] E --> L[(SQLite ledger)] L --> RP[Reports HTML MD JSON SARIF CSV]
NOT_APPLICABLE with a reason you can review.scan.allow_tool_network: true, which is off by default: osv-scanner then sends the package names and versions from your lockfiles to api.osv.dev, and trivy only downloads its vulnerability database. Until it is set they are BLOCKED with a reason that says this, and /pandaward:start offers the switch once. When an override in the workspace root (pnpm.overrides, overrides or resolutions in package.json, or overrides in pnpm-workspace.yaml) replaces a package with a local one (link:, file:, workspace: or portal:), an osv-scanner result for that package is dropped if the lockfile entry is that local package, since the registry package's advisories do not apply to code that is not installed; the adapter line counts them and names the overrides. A result is kept, and named in the adapter line, when the lockfile still pins a registry version or the override is an npm: alias. A gitleaks match whose value is shaped like a placeholder (a run of 8 or more sequential or repeated characters, a word such as dummy, example or changeme, a value starting with test_, a JWT with a short signature or dummy claims, or the fallback after secrets.NAME || in a workflow) is kept but listed as info for review instead of counting against E-005; the value is judged in memory and never stored, a service_role JWT is never treated as a placeholder, and the adapter line says how many were listed. apktool decodes .apk files found in the project (resources only, never the app's code) so the manifest checks also run on what you ship (K-005). If you run [MobSF](https://github.com/MobSF/Mobile-SecuOnly the beginning is shown; read the rest in the repo