DeepYard

Filesystem MCP vs Memory MCP

Side-by-side comparison built from DeepYard's structured catalog. Content updated Aug 21, 2026.

Direct Answer

Filesystem MCP suits teams needing open-source access, file read focus, and 89,768 GitHub stars in current listing data. Memory MCP suits teams needing open-source access, persistent memory focus, and 89,768 GitHub stars in current listing data. This summary reflects catalog metadata only for decision support, not independent testing.

What this comparison weighs

  • Pricing and free-tier availability
  • License model and deployment fit
  • GitHub adoption and contributor depth
  • Catalog tags, integrations, and supported workflows
F

Filesystem MCP

Secure local filesystem access — read, write, search, and manage files via MCP

OSSFree
89.8K19.0K/w2d ago426
M

Memory MCP

Persistent knowledge graph memory across AI coding sessions

OSSFree
89.8K15.0K/w2d ago426
MetricFilesystem MCPMemory MCP
GitHub Stars89.8K89.8K
Contributors426426
Last CommitAug 20, 2026Aug 20, 2026
Open Issues533533
Licenseopen-sourceopen-source
Pricingopen-sourceopen-source
Free TierYesYes
Categorymcp-serversmcp-servers
TrendingNoNo

Choose Filesystem MCP if you need

  • Filesystem MCP is the stronger pick when File Read matters because that capability is listed only on its profile.
  • Filesystem MCP is the cleaner fit if you specifically need Filesystem workflows from the catalog tags.

Choose Memory MCP if you need

  • Memory MCP is the stronger pick when Persistent Memory matters because that capability is listed only on its profile.
  • Memory MCP is the cleaner fit if you specifically need Memory workflows from the catalog tags.

Meaningful differences

    Shared capabilities

    • Anthropic
    • Reference Server

    Shared Tags

    anthropicreference-server

    Only in Filesystem MCP

    filesystemfile-operationsmcp-officiallocal

    Only in Memory MCP

    memoryknowledge-graphpersistencecontext-management

    Limitations and evidence

    • DeepYard compares structured public metadata; this is not an independent benchmark unless a test record is shown.
    • Signals such as stars, contributors, and last commit indicate public activity, not purchase fit or runtime quality.
    • Pricing and feature coverage reflect the stored listing snapshot and may lag vendor changes between refreshes.

    About Filesystem MCP

    The official Anthropic filesystem MCP server provides sandboxed access to your local file system with configurable allowed directories. It exposes tools to read file contents, list directories, write and create files, move files, search by pattern, and get file metadata — giving AI assistants controlled, auditable access to your codebase without arbitrary shell execution. Ships as part of Anthropic's reference MCP servers collection.

    View full listing

    About Memory MCP

    The official Anthropic memory MCP server gives AI assistants persistent, cross-session memory using a local knowledge graph stored as a JSON file. Claude can create entities (people, projects, concepts), record relations between them, and add observations over time — then recall that information in future sessions. Ideal for long-running projects where continuity matters: the assistant remembers your architecture decisions, team conventions, and in-progress work without you having to repeat context.

    View full listing