Related MCP Server Resources

Explore more AI models, providers, and integration options:

  • Explore AI Models
  • Explore AI Providers
  • Explore MCP Servers
  • LangDB Pricing
  • Documentation
  • AI Industry Blog
  • TxtAi Memory Vector Server
  • Jira MCP Server
  • mcp-server-asana
  • IR Toolshed MCP Server
  • Ollama MCP Server
Back to MCP Servers
MCP Server Memory File

MCP Server Memory File

Public
g0t4/mcp-server-memory-file

Enables management of conversational memories via a text file for Model Context Protocol clients, offering add, search, delete, and list functions to enhance context retention and response relevance in AI interactions.

typescript
0 tools
May 30, 2025
Updated Jun 4, 2025

Supercharge Your AI with MCP Server Memory File

MCP Server

Unlock the full potential of MCP Server Memory File through LangDB's AI Gateway. Get enterprise-grade security, analytics, and seamless integration with zero configuration.

Unified API Access
Complete Tracing
Instant Setup
Get Started Now

Free tier available • No credit card required

Instant Setup
99.9% Uptime
10,000+Monthly Requests

mcp-server-memory

This is an MCP server to interact with a memory text file to help Claude with inter-chat context.

Each line is a memory.

These tools allow Claude (and other MCP clients) to manage memories mid-chat:

  • memory_add(memory: string) - append the memory
  • memory_search(query: string) - return matching memories (substring exact match) - later, might allow globs/regex
  • memory_delete(query: string) - delete matching memories (substring exact match)
  • memory_list() - return all memories
  • FYI memory_update == memory_delete + memory_add

For example,

  • I mention my name
    "talking to Wes"
  • metion daughter's age
    "Wes's daughter is 8"
  • say working on a typescript project
    "working on typescript project"
  • AND, this is critical, can be based on things Claude (assistant/LLM) says or does...
    • Notably, tool use (i.e. run_command)... say there is a failure on a first attempt to use the tool (i.e. the python command isn't present) and then a subsequent tool use succeeds (i.e. using python3 instead of python)

      Claude can record "use python3, python is not present"...

  • I ask Claude to get rid of memories about X

    memory_delete(query: X)

  • I correct my name

    memory_search("oldname") + memory_delete(each matching record, or a common subset query) + memory_add("newname")

Then, when a new chat begins, Claude will automatically get recent memories (a subset or all) OR can ask for memories (some/more/all). And then can use those to influence responses/tools/etc.

Design

A simple memory text file, why:

  • ChatGPT's memory works well and is essentially a text file
    • Maybe it's structured behind the scenes, however if you review your memory its presented as a text file.
  • My testing of a similar reminders feature for mcp-server-commands worked great (when Claude had them).
  • Unstructured text simplifies the tooling and parameters to basically managing a list of strings.

Cueing mechanism:

  • It's also important to have a cue for the model to know when to store memories. This is a bit more unclear how best to do this but..
  • Training: OpenAI acknowledges some training of models to know when to store memories. Just like models are trained for tool use.
  • Prompt: A system prompt component likely contains a reminder to trigger storing memories.
  • Tool alone: In my testing of Claude, with a tool spec alone, and even with hints/suggestions in tool responses, I couldn't get Claude to store memories. So this alone is not sufficient. Seems like Claude's training with tools is to only use them in pursuit of the prompt/request and thus why I believe adding a reminder/cue in a prompt component will work well.

TODOs/Ideas

I have no idea if these are worth the time, just listing ideas here for the future. Perhaps in part to stop myself from working on them :)

  • Recency factor: a way to rearrange memories based on recency?
    • Order then becomes relevant for ambiguous memory queries (i.e. work on typescript project and python project then I ask to start a new project, could suggest the most recently used one?)
  • Fade out old memories?
Publicly Shared Threads0

Discover shared experiences

Shared threads will appear here, showcasing real-world applications and insights from the community. Check back soon for updates!

Share your threads to help others
Related MCPs5
  • TxtAi Memory Vector Server
    TxtAi Memory Vector Server

    Model Context Protocol server offering advanced semantic search, persistent memory management, tag-b...

    Added May 30, 2025
  • Jira MCP Server
    Jira MCP Server

    Enables AI assistants to seamlessly interact with Jira via Model Context Protocol, offering project ...

    Added May 30, 2025
  • mcp-server-asana
    mcp-server-asana

    Enables seamless interaction with Asana API via Model Context Protocol, providing advanced task, pro...

    22 tools
    Added May 30, 2025
  • IR Toolshed MCP Server
    IR Toolshed MCP Server

    Provides a Model Context Protocol (MCP) service offering advanced network incident response tools in...

    Added May 30, 2025
  • Ollama MCP Server
    Ollama MCP Server

    Enables seamless integration of local Ollama LLM models with MCP-compatible applications, offering m...

    Added May 30, 2025