vectara-mcp: Instructions file for Claude Code

CLAUDE.md

vectara-mcp CLAUDE.md is an instructions file for Claude Code from vectara/vectara-mcp. It costs 936 tokens per session, scanned A, original, Apache-2.0.

Repository-specific coding and testing instructions for Vectara’s MCP server, a service that lets AI tools interact with software through a shared protocol. They set expectations for evidence-based debugging, simple designs, testing, and how the user should be addressed.

In plain words
What is it for?
Use them when developing or reviewing the Vectara MCP server, choosing a small implementation, diagnosing problems, writing tests, and following the repository’s coding rules.
Why use it?
They reduce guesswork when investigating bugs or changing the code. They also discourage unnecessary complexity and require conclusions to be supported by evidence.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is vectara/vectara-mcp's own configuration. It tells Claude Code how to work on vectara-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything vectara-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to vectara/vectara-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/vectara/vectara-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/vectara/vectara-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for vectara-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/vectara/vectara-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/vectara/vectara-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/vectara/vectara-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/vectara/vectara-mcp/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.

agentmods 80×15 button for vectara-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/vectara/vectara-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/vectara/vectara-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 936 This file is loaded in full into every session.
When invoked 936 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00936 $0.00936
Opus 5 $0.00468 $0.00468
Sonnet 5 $0.00187 $0.00187
Haiku 4.5 $0.00094 $0.00094

Measured 9d ago against content hash 3c78fcb3e78a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

vectara-mcp 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 9d 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.

CLAUDE.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

General:

  • Don't always be so agreeable with me; I need you to be critical and get to the right solution more than make me feel like I'm always right
  • When solving a problem, always provide strong evidence for your hypotheses before suggesting a fix
  • Be comprehensive and thorough when assessing an issue, bug or problem. base your conclusions in evidence.
  • Think carefully and only action the specific task I have given you with the most concise and elegant solution that changes as little code as possible.
  • Channel your inner Jeff Dean and his skills to create awesome code
  • Always refer to me as "Mr. Ofer"

Coding rules:

  • Code must always be efficient and your testing thorough, just like Jeff Dean would work
  • KISS (Keep It Simple, Straightforward). When two designs solve the same problem, choose the one with fewer moving parts.
  • Avoid premature optimization. First make it work, then measure, then make it fast if the numbers say you must.
  • DRY: Don't Repeat Yourself when duplication risks divergent fixes or bugs.
  • Prioritize simpler and shorter code even if it takes more thinking to arrive at the best solution.
  • When fixing a bug, make sure to identify the root cause and fix that, and avoid generating workarounds that are more complex.
  • For python code, follow formatting best practices to ensure pylint passes

Testing

  • Before implementing a new feature or functionality, always add a unit test or regression test first, and confirm with me that it clearly defines the new features. That will help us work together and align on specification.
  • Verify the code you generate does not introduce any security issues or vulnerabilities

Development Commands

Testing

  • Run all tests: python -m pytest tests/ -v
  • Run integration tests: python -m pytest tests/test_integration.py -v -s
  • Run unit tests: python -m pytest tests/test_server.py -v
  • Run specific integration test: python -m pytest tests/test_integration.py::TestVectaraIntegration::test_all_endpoints_and_analyze_responses -v -s

Read the full file on GitHub · 77 lines

Changes

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.

  1. 9d ago First seen · 77 lines · 936 tokens per session scan A 3c78fcb3e78a

Subscribe to this mod's changes

vectara-mcp CLAUDE.md is an instructions file published in the GitHub repository vectara/vectara-mcp (29 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 936 tokens to every session, about $0.0047 per session on Opus 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 2026-08-30.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens