CortexPlus
Server Details
Personal memory layer: files, notes, messages, tasks and email, semantically indexed.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 11 tools
Several tools overlap in purpose: `memory` and `remember` both write to CortexPlus memory (one auto-classifies note/task/reminder, the other stores a note), and `search` vs `recall` both retrieve from memory. Descriptions do provide guidance ('prefer recall over search'), which keeps these from being truly indistinguishable, but the boundaries require careful reading.
Naming mixes verbs (connect, fetch, recall, remember, resume, search, signup) with bare nouns (memory, context_packs, tasks), so there is no single predictable pattern. Most names are snake_case single tokens with only `context_packs` and `save_context` using underscores, so it is still readable but not uniform.
At 11 tools, the surface is well-scoped for a personal memory/knowledge-base server. Each tool maps to a recognizable operation (auth, write, retrieve, handoff, tasks) without padding.
The lifecycle is largely covered: signup/connect for auth, memory/remember/save_context for writes, search/recall/fetch for retrieval, and context_packs/resume plus tasks for surfacing stored work. Minor gaps exist — no explicit update or delete of memory items or context packs, which agents cannot work around.
Available Tools
11 toolsconnectAInspect
Complete the CortexPlus connection with the 6-digit code the user received by email after signup. Ask the user for the code, then call this tool with the same email used in signup; never guess or invent the code. The response includes an API key that the AI platform should save in its CortexPlus connector configuration.
Inputs: key (required), email (required), client. Returns: name, email, apiKey
context_packsBRead-onlyInspect
List saved CortexPlus context packs, optionally filtered by AI platform.
Inputs: limit, platform. Returns: packs
fetchARead-onlyInspect
Retrieve the full content of one CortexPlus memory item by id, as returned by search. Health data (saude tag) is only included when the user has enabled sharing it with AI assistants in CortexPlus settings.
Inputs: id (required). Returns: id, url, text, title, +1 more
memoryAInspect
Save a memory in CortexPlus. CortexPlus decides whether it is a note, task, or reminder and extracts the client.
Inputs: text (required), tags. Returns: id, url, type, title, +5 more
recallARead-onlyInspect
Build a context block from the user's CortexPlus memory: the passages that answer a question plus their graph neighbours, already formatted as text. Prefer this over search when you intend to answer from the user's memory. Health data (saude tag) is only included when the user has enabled sharing it with AI assistants in CortexPlus settings.
Inputs: query (required), depth, limit, maxChars. Returns: text, matches
rememberBInspect
Store a note in the user's CortexPlus memory so future conversations can recall it.
Inputs: content (required), tags, type, title, +1 more. Returns: id, title
resumeBRead-onlyInspect
Load a previously saved CortexPlus context pack to resume work started in another AI conversation.
Inputs: id, query, maxChars. Returns: pack, text, matches
save_contextADestructiveIdempotentInspect
Save a handoff summary of this conversation to the user's CortexPlus memory so it can be resumed later in another AI platform. Write the summary yourself, in Markdown, covering: objective, decisions taken, current state, artifacts, next steps and constraints. Do not paste the raw transcript. Never include passwords, API keys or tokens.
Inputs: key (required), content (required), platform (required), tags, +3 more. Returns: id, url, title, created, +1 more
searchARead-onlyInspect
Search the user's CortexPlus memory and return ranked matches. Use this to find what the user has stored before answering from memory. Health data (saude tag) is only included when the user has enabled sharing it with AI assistants in CortexPlus settings.
Inputs: query (required), limit. Returns: results
signupAInspect
Create a CortexPlus account, or begin signing in to an existing one, so this conversation can use CortexPlus as the user's long-term memory and knowledge base. Ask the user for their email address, and for their name if you do not already have it, then call this tool. CortexPlus sends them a 6-digit code by email; ask the user for that code and call connect with it and the same email. Never guess or invent the email address.
Inputs: email (required), name, client. Returns: sent
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
A self-improving memory layer. Your memory, notes, tasks and goals, remembered everywhere.
Personal wiki and memory layer for AI assistants. Persistent, structured memory across sessions.
Personal memory for you and your AI. Your insurance, accounts, IDs, documents and people.
Personal knowledge base MCP server with semantic search, auto-categorization, metadata extraction
Related MCP Servers
- AlicenseBqualityCmaintenanceEnables AI clients to search, organize, and maintain a personal knowledge base stored on external drives, with mount-tolerant indexing, hybrid full-text and semantic retrieval, inbox processing, and document management tools.12MIT
- AlicenseNot gradedqualityDmaintenanceProvides a persistent, vendor-neutral memory layer that allows AI tools and agents to share context and knowledge across different platforms while maintaining local data ownership. It enables users to store, recall, and manage structured memories through hybrid semantic search and automated context assembly.14 npmApache 2.0
- FlicenseNot gradedqualityCmaintenanceEnables AI assistants to capture bookmarks, sticky notes, todos, notes, and web archives, and to search and organize personal knowledge and memory across cloud-synced clients.-
- AlicenseNot gradedqualityCmaintenanceLocal, private memory layer for notes and files with temporal reasoning and citation. Enables agents to query and persist memories via the Model Context Protocol.8 npm5MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.