Borrowing it
Nothing to install: this file belongs to MWG-Logan/Central-Memory-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.
curl -O https://raw.githubusercontent.com/MWG-Logan/Central-Memory-MCP/main/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/MWG-Logan/Central-Memory-MCPWrote 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/mwg-logan/central-memory-mcp/copilot-instructions)<a href="https://agentmods.dev/instructions/mwg-logan/central-memory-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/mwg-logan/central-memory-mcp/copilot-instructions.svg" alt="Measured on agentmods" 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 | $0.02139 | $0.02139 |
| Opus 5 | $0.01069 | $0.01069 |
| Sonnet 5 | $0.00428 | $0.00428 |
| Haiku 4.5 | $0.00214 | $0.00214 |
Grade A, and why
Central-Memory-MCP copilot-instructions.md scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://localhost:7071/api/health How it starts
The opening of the file, as written. The whole thing — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Central Memory MCP Server (.NET 10 / Azure Functions)
Model Context Protocol (MCP) memory server built with Azure Functions (.NET 10, C# 14, isolated worker) providing persistent knowledge graph storage (Entities + Relations) for AI assistants.
ALWAYS reference these instructions first. Only fall back to ad‑hoc search or shell commands if something here is contradicted by current code.
Technology Stack (Current Rewrite)
- .NET 10 (preview) / C# 14
- Azure Functions isolated worker model
- Azure Functions MCP Extension (McpToolTrigger / McpToolProperty / ToolInvocationContext)
- Azure Table Storage (Entities, Relations, Workspaces tables)
- Azurite (local emulator) for development
- Idempotent upsert logic for Entities and Relations (no duplicates by logical key)
Storage Schema (Current)
Tables
entities: PartitionKey = WorkspaceName, RowKey = Guid (entity Id as N format)relations: PartitionKey = WorkspaceName, RowKey = Guid (relation Id as N format)workspaces: PartitionKey =workspaces, RowKey = workspace name (lowercase)
Entities
- Unique per (WorkspaceName + Name) – Upsert reuses existing Id.
- Stored fields: Id, Name, EntityType, Observations ("||" delimited), Metadata.
Relations
- Unique per (WorkspaceName + FromEntityId + ToEntityId + RelationType) – Upsert reuses existing Id.
- Stored fields: Id, FromEntityId, ToEntityId, RelationType, Metadata.
- Upsert accepts either GUIDs (
fromEntityId/toEntityId) or legacy names (from/to) which are resolved server‑side.
Key Azure Functions (MCP Tools)
Defined in Functions/GraphFunctions.cs using MCP attributes:
read_graph– Return all entities + relations for a workspace.upsert_entity– Create/update entity (idempotent by name).upsert_relation– Create/update relation (idempotent by logical key).get_entity_relations– List relations originating from an entity (acceptsentityIdor legacyentityName).
Health / readiness endpoints: HealthFunctions (/api/health, /api/ready).
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.
- 6d ago First seen · 334 lines · 2,139 tokens per session scan A 3e640e83406d
Central-Memory-MCP copilot-instructions.md is an instructions file published in the GitHub repository MWG-Logan/Central-Memory-MCP (3 stars, last pushed 3mo ago), licensed MIT. It adds 2,139 tokens to every session, about $0.0107 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.
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.
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).
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).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.