Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-prose-memory add that my favorite color is blue"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Persistent memory for MCP clients.
mcp-prose-memory gives an agent a small, durable place to keep facts across sessions. It stores memory as JSON, keeps facts grouped by section, and exposes one tool for careful add, remove, replace, and view operations.
It is built for memory that should survive restarts without becoming a loose text file that slowly drifts out of shape.
Docs · Changelog · Contributing · Security
JSON memory storage with a stable schema
Compact structured facts with optional key, value, source, and confidence
Atomic writes through temp-file replacement
Atomic fact operations: add, remove, replace, view
Sectioned context organization for general clients and local assistant memory
Case-insensitive duplicate detection
Strict line-number validation for remove and replace
Automatic normalization for older or partial JSON documents
Compact memory_context output with section and character-budget filters
Limits: 30 facts per section, 300 characters per fact, 80 characters per structured key
Configurable storage path via environment variable
Related MCP server: agentsmd-memory
Full setup guide: Docs.
Runtime: Node >= 18.
npm install -g mcp-prose-memoryOr run with npx:
npx mcp-prose-memoryConfiguration reference: Docs.
Default storage is ~/.mcp-prose-memory/memory.json. Override it with MEMORY_PATH.
If you used an older release with a client-specific default memory location, either move that JSON file to the new default path or set MEMORY_PATH to the existing file.
Add a server entry like this to your MCP client config:
{
"mcpServers": {
"memory": {
"command": "npx",
"args": ["mcp-prose-memory"]
}
}
}Add a server entry like this to your CLI MCP config:
{
"mcpServers": {
"memory": {
"command": "npx",
"args": ["mcp-prose-memory"]
}
}
}{
"mcpServers": {
"memory": {
"command": "npx",
"args": ["mcp-prose-memory"],
"env": {
"MEMORY_PATH": "/path/to/your/memory.json"
}
}
}
}The memory file is JSON with arrays of facts per section:
{
"version": 5,
"updated": "2025-01-15T10:30:00.000Z",
"sections": {
"work": ["Fact 1", "Fact 2"],
"personal": ["Lives in Berlin", "Prefers dark mode"],
"top_of_mind": [],
"history": ["Completed project X"],
"instructions": ["Be concise"],
"user_preferences": [
{
"key": "answer_style",
"value": "Prefers concise answers",
"confidence": "high",
"source": "user_explicit",
"createdAt": "2025-01-15T10:30:00.000Z",
"updatedAt": "2025-01-15T10:30:00.000Z"
}
]
}
}If the file does not exist, the server starts with an empty document. If the file is invalid JSON, the server fails the operation instead of wiping memory.
Tools reference: Docs.
Single tool for all memory operations. The command parameter selects the action.
Commands:
Show all memories or filter by section.
{"command": "view"}
{"command": "view", "section": "work"}Add a fact to a section.
{"command": "add", "section": "personal", "fact": "Lives in Berlin"}Structured compact facts are also supported:
{"command": "add", "section": "user_preferences", "key": "answer_style", "value": "Prefers concise answers"}Add a structured fact or replace the existing fact with the same key.
{"command": "upsert", "section": "user_preferences", "key": "answer_style", "value": "Prefers concise and direct answers"}Remove a fact by line number.
{"command": "remove", "section": "work", "line": 3}Update a fact by line number.
{"command": "replace", "section": "top_of_mind", "line": 1, "fact": "Working on new project"}Returns memory for session initialization. Clients can request compact bounded context.
{}{"format": "compact", "sections": ["user_profile", "user_preferences"], "maxChars": 1500}Section | Purpose |
| Professional context, projects, colleagues, tools |
| Location, preferences, interests, personal facts |
| Current focus, active tasks |
| Past events, completed work |
| Standing rules, behavioral preferences |
| Stable user profile facts |
| Durable preferences |
| Eyra-specific product and architecture facts |
| Durable local environment facts |
| Repeated workflow preferences |
| Writing and tone preferences |
| Durable task context |
| Explicitly requested durable reminders |
git clone https://github.com/gabrimatic/mcp-prose-memory.git
cd mcp-prose-memory
npm ci
npm test
npm run checknpm test builds the TypeScript source and runs store-level plus real MCP stdio smoke tests. npm run check also runs a production dependency audit and verifies the npm package contents with npm pack --dry-run.
prepublishOnly runs the same check before publishing.
Changes: CHANGELOG.md
Contributions: CONTRIBUTING.md
Security reports: SECURITY.md
Issues: GitHub Issues
By Soroush
MIT
Manage persistent memory across sessions.
Commands:
view: Show all memories (optionally filter by section)
add: Add a new fact to a section
upsert: Add or replace a structured fact by key
remove: Remove a fact by section and line number
replace: Update a fact by section and line number
Sections: work, personal, top_of_mind, history, instructions, user_profile, user_preferences, eyra_project, devices_environment, workflows, writing_style, long_term_tasks, do_not_forget
Examples:
{"command": "view"}
{"command": "view", "section": "work"}
{"command": "add", "section": "personal", "fact": "Lives in Berlin"}
{"command": "upsert", "section": "user_preferences", "key": "answer_style", "value": "Prefers concise answers"}
{"command": "remove", "section": "work", "line": 3}
{"command": "replace", "section": "top_of_mind", "line": 1, "fact": "Working on new project"}
| Name | Required | Description | Default |
|---|---|---|---|
| command | Yes | Operation to perform | |
| section | No | Target section (required for add/remove/replace, optional for view) | |
| sections | No | Optional section allowlist for compact view/context output | |
| fact | No | For add/replace: the fact to store (max 300 chars) | |
| key | No | Stable compact key for structured facts | |
| value | No | Compact value for structured facts | |
| source | No | Short source label for structured facts | |
| confidence | No | Confidence label for structured facts | |
| line | No | For remove/replace: line number within section (1-indexed) | |
| format | No | Output format for view | |
| maxChars | No | Maximum characters for view output |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description must carry the burden of behavioral disclosure. It describes operations and constraints (e.g., max lengths) but does not mention side effects, save guarantees, or performance impacts.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Well-structured with sections for commands, sections, and examples. Slightly verbose due to listing all sections, but the structure aids readability.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers all 11 parameters with examples and command details. No output schema is provided, but the description sufficiently explains what each command does. However, it does not describe return values or error handling.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema has 100% description coverage, so baseline is 3. The description groups parameters by command and provides examples, which adds some value but does not significantly extend beyond the schema's parameter descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it manages persistent memory across sessions. Lists specific commands (view, add, upsert, remove, replace) and sections, distinguishing it from the sibling tool 'memory_context' which likely provides context retrieval.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit commands and sections, but does not contrast with the sibling 'memory_context' to clarify when to use this tool vs. the other. However, the examples and command list make usage clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Load memory for session start. Supports compact bounded context for clients with small prompt budgets.
| Name | Required | Description | Default |
|---|---|---|---|
| maxChars | No | ||
| sections | No | ||
| format | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, so the description adds value by noting 'compact bounded context', implying the tool may limit output size. This goes beyond the annotation, though it could be more explicit about whether state is affected or if data is cached. No contradiction with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with the primary purpose. No superfluous words; each sentence adds unique information. The structure is efficient and easy to parse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Considering 3 undocumented parameters and no output schema, the description is insufficient. It does not explain return values, how sections filter memory, or the behavior of format. The sibling 'memory' is not differentiated in usage. The tool needs more context for an agent to use it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage, the description must explain parameters but does not. It hints at 'compact bounded context' which relates to maxChars and possibly format, but does not clarify what 'sections' represent or how format options differ. Agents would lack understanding of each parameter's semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Load memory' and the resource 'memory', specifying the context 'for session start'. It also distinguishes from the sibling 'memory' by highlighting 'compact bounded context for clients with small prompt budgets', which implies a focused subset.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage at session start and for clients with small prompt budgets, but does not explicitly state when not to use it or mention the sibling 'memory' as an alternative. The guidance is suggestive but lacks clear exclusions or comparisons.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v3.1.0memorymemory_contextThe two tools have clearly distinct purposes: 'memory' handles CRUD operations on memories, while 'memory_context' loads memory for session start. No overlap or ambiguity.
Both tool names start with 'memory' and use underscores for compound names, following a consistent pattern. However, 'memory' is a single noun while 'memory_context' is a compound noun, a minor deviation.
With only 2 tools, the server is lean. All CRUD operations are bundled into one tool, which works but limits granularity. The count is on the low side but acceptable given the internal richness.
The 'memory' tool covers all standard CRUD operations (view, add, upsert, remove, replace), and 'memory_context' handles context loading. Minor gaps like listing sections or clearing all memories are missing but not critical.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Shared, governed long-term memory for AI agents across tools and sessions via MCP and REST.
An MCP memory server. One memory your agents share — across models, devices and apps.
Cloud-hosted MCP server for durable AI memory
Persistent, inspectable memory for AI agents with lineage, correction, and a hosted MCP endpoint.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/gabrimatic/mcp-prose-memory'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
