What is mcp-server CLAUDE.md?

A set of instructions for using persistent project memory with Claude Code. The memory stores decisions, conventions, bug fixes, preferences, and other facts so they can be recalled in later sessions.

Use it when maintaining a project across multiple coding sessions. It helps remember architecture choices, coding practices, previous fixes, environment details, and information about specific files or modules.

It reduces repeated explanations and helps prevent the agent from forgetting earlier decisions or project rules. It also encourages checking relevant past context before starting work.

How sharedmemoryai/mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to sharedmemoryai/mcp-server. 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/sharedmemoryai/mcp-server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/sharedmemoryai/mcp-server

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/sharedmemoryai/mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/sharedmemoryai/mcp-server/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/sharedmemoryai/mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/sharedmemoryai/mcp-server/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/sharedmemoryai/mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/sharedmemoryai/mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 620 This file is loaded in full into every session.

When invoked 620 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.

Model	Per session	Once invoked
Fable 5.1	$0.00620	$0.00620
Opus 5.5	$0.00248	$0.00248
Sonnet 5.5	$0.00124	$0.00124
Haiku 4.5	$0.00062	$0.00062

Measured 2mo ago against content hash b4ad10957980, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-server 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 2mo 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 · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SharedMemory — Persistent Memory for AI Agents

You have access to SharedMemory via MCP tools. Use it to persist knowledge across sessions and recall past context.

When to Remember (Proactively)

Store these automatically, without being asked:

Decisions: Architecture choices, technology selections, trade-off resolutions ("Chose Postgres over MongoDB because...")
Project conventions: Coding patterns, naming rules, folder structure, test practices
Bug fixes: Root cause, investigation path, what was tried, and the solution
User preferences: Editor settings, formatting style, communication preferences
Environment facts: Deployment targets, CI/CD setup, credentials locations, URLs
Key learnings: Gotchas, non-obvious behaviors, performance findings

When to Recall (Before Acting)

Check memory before:

Starting a new task → query with the task description to find relevant context
Making architectural decisions → query for past decisions and conventions
Debugging → query for similar past bugs and solutions
Working with a specific file/module → get_entity for that component
Starting a new session → get_context to load relevant project knowledge

Tools Available

Tool	When to Use
`remember`	Store a fact, decision, preference, or learning
`query`	Search for relevant memories by meaning
`batch_remember`	Store multiple related facts at once (up to 100)
`get_entity`	Get everything known about a person, project, file, or concept
`search_entities`	Find entities by name
`get_graph`	See the full knowledge graph for a volume
`get_context`	Get a formatted context block for the current task
`get_profile`	Get the auto-generated user profile
`get_memory`	Retrieve a specific memory by ID
`delete_memory`	Delete a memory
`update_memory`	Update a memory
`feedback`	Rate a memory's relevance (positive/negative)
`list_volumes`	List available memory volumes
`list_documents`	List uploaded documents

Read the full file on GitHub · 53 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.

2mo ago First seen · 53 lines · 620 tokens per session scan A b4ad10957980

Subscribe to this mod's changes

mcp-server CLAUDE.md is an instructions file published in the GitHub repository sharedmemoryai/mcp-server (1 stars, last pushed 5mo ago), licensed MIT. It adds 620 tokens to every session, about $0.0025 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.

Memory and context

mcp-server CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-server CLAUDE.mdsharedmemoryai/mcp-server	Instructions file	1	5mo ago	MIT	A	620	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

mcp-server: Instructions file for Claude Code