Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/candorsystems/candor-financeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/candorsystems/candor-finance/candor)<a href="https://agentmods.dev/mcp/candorsystems/candor-finance/candor"><img src="https://agentmods.dev/badge/mcp/candorsystems/candor-finance/candor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/candorsystems/candor-finance/candor"><img src="https://agentmods.dev/badge/mcp/candorsystems/candor-finance/candor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
candor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed 9dce3a106eb6
- yesterday Changed 9248c9813310
- 2d ago Changed 36a3524aed09
- 3d ago Changed 79bc6cb3cf0d
- 4d ago Changed 80ca2e9f2c64
- 5d ago Changed a6554bcd6af8
- 7d ago Changed cd540f356514
- 11d ago First seen · 10 lines scan A 5f0ace3d35b2
candor is an MCP server published in the GitHub repository candorsystems/candor-finance (2 stars, last pushed today), with no licence file. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
safe-docx
AI-native surgical editing of existing Word .docx files with formatting preservation. Runs locally from the @usejunior/safe-docx npm package.
firestore
A CLI tool for running a toolbox server. Runs locally from the @toolbox-sdk/server npm package.
horizon-shield-webmcp
Agent intake desk for property renovation. Read only, CORS open, fail closed, receipts recompute. Remote server at web.horizonshield.dev.
justfill-pdf-forms
Fill existing PDF forms from JSON or Excel with MCP agents; review fields and reuse templates. Runs locally from the justfill-mcp Python package. Needs 1 environment variable to run.
mcp-spendee
MCP server "mcp-spendee" as configured in gibsn/mcp-spendee. Runs locally from the mcp-spendee Python package.
toolrouter
MCP server "toolrouter", hosted remotely at api.toolrouter.com, as configured in Humanleap/toolrouter-mcp.