Borrowing it
Nothing to install: this file belongs to tallyfy/mcp-public. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tallyfy/mcp-public/main/CLAUDE.mdgit clone --depth 1 https://github.com/tallyfy/mcp-publicWrote 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/instructions/tallyfy/mcp-public/claude-md)<a href="https://agentmods.dev/instructions/tallyfy/mcp-public/claude-md"><img src="https://agentmods.dev/badge/instructions/tallyfy/mcp-public/claude-md/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/instructions/tallyfy/mcp-public/claude-md"><img src="https://agentmods.dev/badge/instructions/tallyfy/mcp-public/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00490 | $0.00490 |
| Opus 5.5 | $0.00196 | $0.00196 |
| Sonnet 5.5 | $0.00098 | $0.00098 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
mcp-public CLAUDE.md 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 3d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 27 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — tallyfy/mcp-public
This repository is an automatically generated, read-only mirror
The code here is a sanitized, server-only snapshot of Tallyfy's MCP server. The canonical source is maintained in a private Tallyfy repository. On every production release, a GitHub Actions workflow assembles an allowlisted subset of the private repo, runs fail-closed secret/internal-pattern scans, and force-syncs the result here.
Do not edit files in this repo directly. Any change is overwritten on the next sync. There is no value in opening a pull request against this mirror; it cannot be merged upstream from here.
- To change the server code, edit it in the private source repo.
- To change these public docs (this file or
README.md), editpublic-mirror/CLAUDE.public.md/public-mirror/README.public.mdin the private repo. They are overlaid into this mirror at publish time.
What is and is not here
Published: the MCP server itself (server/ — tools, routes, middleware, utils), server.json, LICENSE, architecture.mmd, this README.md/CLAUDE.md, and .env.example.
Deliberately not published (kept private): hosting/WebSocket layer, monitoring and alerting, deployment workflows, internal runbooks, and any infrastructure identifiers. This mirror is the source you can read and run, not the infrastructure that runs the managed endpoint.
Using the server
- Hosted endpoint:
https://mcp.tallyfy.com/(streamable HTTP, OAuth against a Tallyfy account). - Run locally: see
README.md(Docker, or Python 3.11 +server/requirements.txt). - Tools: 131, scoped to the authenticated user. Most call the public Tallyfy API as that user.
search_product_docsreads the public docs search index (no credentials, no org data),get_org_context/update_org_contextread and write the server-side org memory store, andvalidate_template_mappingand the threeask_user_*tools do their work without calling the API.
Reporting issues
Security issues: [email protected]. Product questions: https://tallyfy.com/contact/.
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.
- 3d ago Changed 5a64d6e9eed7
- 10d ago Changed fb575312886e
- 1mo ago Changed 90fdf207e48b
- 1mo ago Changed da085e354246
- 1mo ago Changed · +21 tokens per session ff138064cc72
- 2mo ago Changed b24090d7a09c
- 2mo ago First seen · 27 lines · 469 tokens per session scan A c6065926dff8
mcp-public CLAUDE.md is an instructions file published in the GitHub repository tallyfy/mcp-public (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 490 tokens to every session, about $0.0020 per session on Opus 5.5. 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.
mcp-public CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-public CLAUDE.mdtallyfy/mcp-public | Instructions file | 1 | 2d ago | Apache-2.0 | A | 490 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 150k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,086 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 282k | 3d ago | MIT | A | 4,335 | Codex, OpenCode |