Skip to main content
Glama
Y-Sky-bro

nexus-memory

by Y-Sky-bro
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

save

Record new information, preferences, or experiences by saving a memory to a tiered storage system. Creates a markdown file with frontmatter for organized retrieval.

Instructions

Save a new memory to a specified tier. Creates a markdown file with frontmatter. Use for recording new information, preferences, or experiences.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tierYesMemory tier: episodic (experiences), semantic (facts/preferences), procedural (workflows), reflection (meta), working (in-session)
nameYesFilename slug (no extension, use dashes: my-memory-name)
contentYesFull markdown content of the memory (including title heading)
tagsNoComma-separated tags (optional)

Implementation Reference

  • nexus_mcp.py:136-152 (schema)
    Input schema definition for the 'save' tool, defining required parameters (tier, name, content) and optional tags.
        "name": "save",
    "description": "Save a new memory to a specified tier. Creates a markdown file with frontmatter. Use for recording new information, preferences, or experiences.",
    "inputSchema": {
        "type": "object",
        "properties": {
            "tier": {
                "type": "string",
                "enum": ["episodic", "semantic", "procedural", "reflection", "working"],
                "description": "Memory tier: episodic (experiences), semantic (facts/preferences), procedural (workflows), reflection (meta), working (in-session)",
            },
            "name": {"type": "string", "description": "Filename slug (no extension, use dashes: my-memory-name)"},
            "content": {"type": "string", "description": "Full markdown content of the memory (including title heading)"},
            "tags": {"type": "string", "description": "Comma-separated tags (optional)"},
        },
        "required": ["tier", "name", "content"],
    },
},
  • nexus_mcp.py:218-260 (handler)
    Handler for the 'save' tool. Maps tier to directory, creates a markdown file with YAML frontmatter (type, strength, dates, tags, links, source, access_count), and returns the relative path on success.
        elif name == "save":
        tier = args["tier"]
        name_slug = args["name"]
        content = args["content"]
        tags = args.get("tags", "")

        tier_dir_map = {
            "episodic": "episodic",
            "semantic": "semantic",
            "procedural": "procedural",
            "reflection": "reflections",
            "working": "working",
        }
        dir_name = tier_dir_map.get(tier)
        if not dir_name:
            return None, {"code": -32602, "message": f"Invalid tier: {tier}"}

        target_dir = os.path.join(MEMORY_DIR, dir_name)
        os.makedirs(target_dir, exist_ok=True)
        filepath = os.path.join(target_dir, name_slug + ".md")

        if os.path.exists(filepath):
            return None, {"code": -32602, "message": f"Memory already exists: {name_slug}.md"}

        today = date.today().isoformat()
        tag_line = f"  tags: [{tags}]" if tags else "  tags: []"
        frontmatter = f"""---
type: {tier}
strength: 1.0
created: {today}
updated: {today}
{tag_line}
links: ""
source: mcp
access_count: 1
last_accessed: {today}
---

{content}
"""
        with open(filepath, "w", encoding="utf-8") as f:
            f.write(frontmatter)
        return {"content": [{"type": "text", "text": f"Saved: {os.path.relpath(filepath, MEMORY_DIR)}"}]}, None
  • nexus_mcp.py:120-170 (registration)
    Registration of all tools including 'save' in the TOOL_DEFS list, returned via handle_tools_list.
    TOOL_DEFS = [
    {
        "name": "search",
        "description": "Search across all memory files by keyword. Returns matching file names, titles, strengths, and context snippets.",
        "inputSchema": {
            "type": "object",
            "properties": {"query": {"type": "string", "description": "Keyword or phrase to search for"}},
            "required": ["query"],
        },
    },
    {
        "name": "stats",
        "description": "Show memory health statistics: file counts per tier, average strength, active/decaying/archived counts.",
        "inputSchema": {"type": "object", "properties": {}},
    },
    {
        "name": "save",
        "description": "Save a new memory to a specified tier. Creates a markdown file with frontmatter. Use for recording new information, preferences, or experiences.",
        "inputSchema": {
            "type": "object",
            "properties": {
                "tier": {
                    "type": "string",
                    "enum": ["episodic", "semantic", "procedural", "reflection", "working"],
                    "description": "Memory tier: episodic (experiences), semantic (facts/preferences), procedural (workflows), reflection (meta), working (in-session)",
                },
                "name": {"type": "string", "description": "Filename slug (no extension, use dashes: my-memory-name)"},
                "content": {"type": "string", "description": "Full markdown content of the memory (including title heading)"},
                "tags": {"type": "string", "description": "Comma-separated tags (optional)"},
            },
            "required": ["tier", "name", "content"],
        },
    },
    {
        "name": "touch",
        "description": "Boost a memory's strength (simulate access, counteracts Ebbinghaus decay). Use this when a memory is referenced or found relevant.",
        "inputSchema": {
            "type": "object",
            "properties": {
                "name": {"type": "string", "description": "Memory filename (with or without .md extension)"},
                "boost": {"type": "number", "description": "Strength boost amount (default 0.15, max 1.0)"},
            },
            "required": ["name"],
        },
    },
    {
        "name": "decay",
        "description": "Run a dry-run decay check. Calculates Ebbinghaus decay for all memories and reports which would be archived. Does NOT modify any files.",
        "inputSchema": {"type": "object", "properties": {}},
    },
]
  • nexus_mcp.py:172-174 (registration)
    handle_tools_list returns TOOL_DEFS which includes the 'save' tool definition.
    def handle_tools_list(req_id):
    return {"tools": TOOL_DEFS}
  • nexus_mcp.py:176-330 (handler)
    Routing in handle_tools_call dispatches to the 'save' branch when name == 'save'.
    def handle_tools_call(req_id, name, args):
    if name == "search":
        query = args.get("query", "").lower()
        if not query:
            return {"content": [{"type": "text", "text": "No query provided."}]}, None
        files = list_memory_files()
        results = []
        for f in files:
            with open(os.path.join(MEMORY_DIR, f["path"]), encoding="utf-8") as fh:
                text = fh.read().lower()
            if query in text:
                lines = text.splitlines()
                snippets = []
                for i, line in enumerate(lines):
                    if query in line.lower():
                        start = max(0, i - 1)
                        end = min(len(lines), i + 2)
                        snippet = "\n".join(lines[start:end]).strip()
                        if len(snippet) > 200:
                            snippet = snippet[:200] + "..."
                        snippets.append(snippet)
                results.append({
                    "title": f["title"] or f["name"],
                    "path": f["path"],
                    "tier": f["tier"],
                    "strength": f["strength"],
                    "snippets": snippets[:3],
                })
        if not results:
            return {"content": [{"type": "text", "text": f"No memories matched '{query}'."}]}, None
        lines = [f"Found {len(results)} memory(s) for '{query}':", ""]
        for r in results:
            lines.append(f"  [{r['tier']}] {r['title']}  (strength: {r['strength']:.2f})")
            lines.append(f"         path: {r['path']}")
            for s in r["snippets"]:
                lines.append(f"         > {s}")
            lines.append("")
        return {"content": [{"type": "text", "text": "\n".join(lines)}]}, None

    elif name == "stats":
        return {"content": [{"type": "text", "text": calc_stats()}]}, None

    elif name == "save":
        tier = args["tier"]
        name_slug = args["name"]
        content = args["content"]
        tags = args.get("tags", "")

        tier_dir_map = {
            "episodic": "episodic",
            "semantic": "semantic",
            "procedural": "procedural",
            "reflection": "reflections",
            "working": "working",
        }
        dir_name = tier_dir_map.get(tier)
        if not dir_name:
            return None, {"code": -32602, "message": f"Invalid tier: {tier}"}

        target_dir = os.path.join(MEMORY_DIR, dir_name)
        os.makedirs(target_dir, exist_ok=True)
        filepath = os.path.join(target_dir, name_slug + ".md")

        if os.path.exists(filepath):
            return None, {"code": -32602, "message": f"Memory already exists: {name_slug}.md"}

        today = date.today().isoformat()
        tag_line = f"  tags: [{tags}]" if tags else "  tags: []"
        frontmatter = f"""---
type: {tier}
strength: 1.0
created: {today}
updated: {today}
{tag_line}
links: ""
source: mcp
access_count: 1
last_accessed: {today}
---

{content}
"""
        with open(filepath, "w", encoding="utf-8") as f:
            f.write(frontmatter)
        return {"content": [{"type": "text", "text": f"Saved: {os.path.relpath(filepath, MEMORY_DIR)}"}]}, None

    elif name == "touch":
        target = args["name"]
        boost = min(float(args.get("boost", 0.15)), 1.0)
        target_lower = target.lower().replace(".md", "")

        files = list_memory_files()
        match = None
        for f in files:
            if f["name"].lower() == target_lower:
                match = f
                break
        if not match:
            return None, {"code": -32602, "message": f"Memory not found: {target}"}

        filepath = os.path.join(MEMORY_DIR, match["path"])
        with open(filepath, encoding="utf-8") as fh:
            text = fh.read()

        old_s = match["strength"]
        new_s = min(old_s + boost, 1.0)
        text = re.sub(r'^(strength:\s*)[\d.]+', rf'\g<1>{new_s:.2f}', text, flags=re.MULTILINE)
        text = re.sub(r'^(\s+strength:\s*)[\d.]+', rf'\g<1>{new_s:.2f}', text, flags=re.MULTILINE)

        today = date.today().isoformat()
        if re.search(r'last_accessed:', text):
            text = re.sub(r'^(last_accessed:\s*).*', rf'\g<1>{today}', text, flags=re.MULTILINE)
            text = re.sub(r'^(\s+last_accessed:\s*).*', rf'\g<1>{today}', text, flags=re.MULTILINE)
        if re.search(r'access_count:', text):
            ac = parse_frontmatter(text, "access_count")
            new_ac = int(ac) + 1 if ac else 1
            text = re.sub(r'^(access_count:\s*)\d+', rf'\g<1>{new_ac}', text, flags=re.MULTILINE)
            text = re.sub(r'^(\s+access_count:\s*)\d+', rf'\g<1>{new_ac}', text, flags=re.MULTILINE)

        with open(filepath, "w", encoding="utf-8") as fh:
            fh.write(text)
        return {"content": [{"type": "text", "text": f"Touched {target}: strength {old_s:.2f} → {new_s:.2f}"}]}, None

    elif name == "decay":
        files = list_memory_files()
        today_epoch = datetime.now().timestamp()
        decay_map = {
            "semantic": 90, "episodic": 30, "procedural": 180,
            "reflection": 60, "working": 7, "core": 999999,
        }
        results_lines = ["Decay check (dry-run):", ""]
        for f in files:
            with open(os.path.join(MEMORY_DIR, f["path"]), encoding="utf-8") as fh:
                text = fh.read()
            created = parse_frontmatter(text, "created") or "2026-05-18"
            try:
                dt = datetime.strptime(created[:10], "%Y-%m-%d")
                days = max(1, (datetime.now() - dt).days)
            except ValueError:
                days = 1
            dc = decay_map.get(f["type"], 30)
            new_s = f["strength"] * math.exp(-days / dc)
            new_s = max(0.05, min(1.0, new_s))
            if abs(new_s - f["strength"]) > 0.01:
                status = ""
                if new_s < 0.2:
                    status = " [WOULD ARCHIVE]"
                elif new_s < 0.4:
                    status = " [DECAYING]"
                results_lines.append(f"  {f['name']}: {f['strength']:.2f} → {new_s:.2f} ({days}d){status}")
        if len(results_lines) == 2:
            results_lines.append("  All memories at expected strength.")
        return {"content": [{"type": "text", "text": "\n".join(results_lines)}]}, None

    return None, {"code": -32601, "message": f"Unknown tool: {name}"}

Tool Definition Quality

B3.3/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must carry full behavioral disclosure. It mentions file creation and markdown format but omits side effects, permissions, or changes to existing data. The agent lacks critical safety context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences are efficient and front-loaded with the main action. Every sentence adds value without unnecessary elaboration.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 4 parameters and no output schema, the description covers the basic purpose and usage but lacks details on return value, error handling, and edge cases. It is adequate but not thorough.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with detailed descriptions for each parameter. The description adds minimal extra meaning beyond 'creates a markdown file with frontmatter,' which does not significantly enhance parameter understanding beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it saves a new memory to a tier and creates a markdown file with frontmatter. It is specific about the verb ('Save') and resource ('a new memory'), though it does not explicitly differentiate from sibling tools like decay or search.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides a use case ('Use for recording new information, preferences, or experiences') but lacks instructions on when not to use or explicit alternatives among siblings. Usage is implied rather than clearly bounded.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Y-Sky-bro/nexus-memory'

If you have feedback or need assistance with the MCP directory API, please join our Discord server