by momentohq
Provides a Model Context Protocol server that interfaces with Momento Cache to perform get, set, and cache management operations via simple command‑line tools.
Mcp Momento implements a Model Context Protocol (MCP) server for Momento Cache, exposing cache primitives (get, set) and control‑plane commands (list‑caches, create‑cache, delete‑cache) through a lightweight Node.js process.
export MOMENTO_API_KEY="your-api-key"
export MOMENTO_CACHE_NAME="your-cache-name" # optional, defaults to "mcp-momento"
export DEFAULT_TTL_SECONDS=60 # optional, defaults to 60
npx -y @modelcontextprotocol/inspector npx @gomomento/mcp-momento@latest
Or use the JSON configuration format for tools like Claude Desktop.get
): returns Hit
, Miss
, or Error
.set
): writes a string value with optional TTL.list-caches
– list all caches in the account.create-cache
– create a new cache.delete-cache
– delete an existing cache.mcp-momento
with a 60‑second TTL.@gomomento/mcp-momento
) and works out‑of‑the‑box with npx
.Q: Do I need a super‑user API key for all commands?
A: Only the control‑plane commands (list-caches
, create-cache
, delete-cache
) require a super‑user key. get
and set
work with regular cache keys.
Q: What data types are supported? A: Keys and values are plain strings. Binary data must be base64‑encoded before storage.
Q: How is TTL handled?
A: If a TTL is supplied to set
, the entry expires after the specified number of seconds. Otherwise the default TTL (DEFAULT_TTL_SECONDS
) is used.
Q: Can I run the server without building from source?
A: Yes. The pre‑built package can be launched directly via npx
as shown above.
Q: Is there a way to customize the cache name at runtime?
A: Set the MOMENTO_CACHE_NAME
environment variable before starting the server.
A simple Model Context Protocol (MCP) server implementation for Momento Cache.
Available on npmjs as @gomomento/mcp-momento
get
key
string -- the key to look up in the cache.cacheName
string -- the name cache where the key presides (optional)Hit
with the found value if the key was found.Miss
if the key was not found.Error
if the request failed.set
key
: string -- the key to set in the cachevalue
: string -- the value to set for the given keyttl
: integer -- the number of seconds to keep this value in the cache (optional)cacheName
: string -- the name of the cache to store the key in (optional)Success
if the key was successfully written to the cache.Error
if the request failed.list-caches
Success
with a comma separated list of cache namesError
if the request failedcreate-cache
name
: string - the name of the cache to createSuccess
if the cache was successfully createdError
if the request faileddelete-cache
name
: string - the name of the cache to deleteSuccess
if the cache was successfully deletedError
if the request failedGet a Momento API key from the Momento Console. Note - to run control plane tools (list-caches
, create-cache
, delete-cache
), you must use a super user API key.
Set environment variables to configure the cache name and Time To Live (TTL) for items in the cache.
# required
export MOMENTO_API_KEY="your-api-key"
# optional
export MOMENTO_CACHE_NAME="your-cache-name"
export DEFAULT_TTL_SECONDS=60
If you do not set these values, it will use mcp-momento
as the cache name and 60 seconds
for the default time to live.
npx -y @modelcontextprotocol/inspector npx @gomomento/mcp-momento@latest
Note: if you're using nodenv
, replace the plain npx
with the path to your npx binary (e.g. /Users/username/.nodenv/shims/npx
).
{
"mcpServers": {
"momento": {
"command": "npx",
"args": [
"-y",
"@gomomento/mcp-momento"
],
"env": {
"MOMENTO_API_KEY": "your-api-key",
"MOMENTO_CACHE_NAME": "your-cache-name",
"DEFAULT_TTL_SECONDS": 60
}
}
}
}
Install dependencies:
npm install
Build the server:
npm run build
Run with MCP Inspector
export MOMENTO_API_KEY="your-api-key"
npx @modelcontextprotocol/inspector node dist/index.js
Please log in to share your review and rating for this MCP.
{ "mcpServers": { "momento": { "command": "npx", "args": [ "-y", "@gomomento/mcp-momento" ], "env": { "MOMENTO_API_KEY": "<YOUR_API_KEY>", "MOMENTO_CACHE_NAME": "mcp-momento", "DEFAULT_TTL_SECONDS": "60" } } } }
Discover more MCP servers with similar functionality and use cases
by topoteretes
Enables AI agents to store, retrieve, and reason over past conversations, documents, images, and audio transcriptions by loading data into graph and vector databases with minimal code.
by basicmachines-co
Basic Memory is a local-first knowledge management system that allows users to build a persistent semantic graph from conversations with AI assistants. It addresses the ephemeral nature of most LLM interactions by providing a structured, bi-directional knowledge base that both humans and LLMs can read and write to.
by smithery-ai
mcp-obsidian is a connector that allows Claude Desktop to read and search an Obsidian vault or any directory containing Markdown notes.
by qdrant
Provides a semantic memory layer on top of the Qdrant vector search engine, enabling storage and retrieval of information via the Model Context Protocol.
by GreatScottyMac
A database‑backed MCP server that stores project decisions, progress, architecture, custom data, and vector embeddings, allowing AI assistants in IDEs to retrieve precise, up‑to‑date context for generation tasks.
by StevenStavrakis
Enables AI assistants to read, create, edit, move, delete, and organize notes and tags within an Obsidian vault.
by mem0ai
Provides tools to store, retrieve, and semantically search coding preferences via an SSE endpoint for integration with MCP clients.
by graphlit
Enables integration between MCP clients and the Graphlit platform, providing ingestion, retrieval, RAG, and publishing capabilities across a wide range of data sources and tools.
by chroma-core
Provides vector, full‑text, and metadata‑based retrieval powered by Chroma for LLM applications, supporting in‑memory, persistent, HTTP, and cloud clients as well as multiple embedding functions.