nexusm-mcp-server
This MCP server lets MCP clients use Nexusm's memory, context, knowledge, and feedback capabilities through four tools.
nexus.context_retrieve: retrieve relevant memories, recent conversation turns, and knowledge entities in one call for open-ended queries, returning aretrieve_idfor later feedback.nexus.memory_search: run targeted semantic or hybrid (vector + trigram) searches over memories with filters likememory_type,limit, andscore_threshold.nexus.memory_create: persist a new memory (episodic, semantic, or procedural) with content, metadata, and optional temporal validity fields.nexus.memory_feedback: submit per-memory usefulness ratings (1-5) and optional reasons for a previouscontext_retrievecall using itsretrieve_id.Transport: usable via stdio and Streamable HTTP MCP transports.
Exposes Prometheus metrics for monitoring the MCP server's performance and usage, including cardinality guards.
Click on "Deploy 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., "@nexusm-mcp-server search memory for recent conversations about Q3 planning"
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.
nexusm-mcp-server
Nexusm MCP Server — generic MCP server exposing Nexusm core capabilities (memory, conversation, knowledge, feedback, context) to MCP clients via @modelcontextprotocol/sdk stdio + Streamable HTTP transports.
Published to npm as @nexusm/mcp-server.
Tracked in Nexusm main repo:
packages/nexusm-mcp-server(US-037 v7.0).
Configuration
Set via environment (e.g. the env block of your client's .mcp.json):
Env var | Required | Purpose |
| yes | Base URL of the Nexus REST API. The server auto-appends |
| yes | Nexus API key (the product auth contract) |
| yes | Tenant id for the compound-id isolation |
| no | Single-user pin. When set to a non-empty value, the server uses it as |
| no | Opt-in Prometheus |
The Nexus API auth contract is
NEXUS_API_TOKEN. Any deployment-edge access control in front of the API (e.g. a reverse proxy / gateway / Cloudflare Access) is not this client's concern — handle it transparently at the network/transport layer (pointNEXUS_API_URLat a local proxy) so the client stays deployment-agnostic. When pointing at a local proxy, setNEXUS_API_URLto the proxy origin (e.g.http://localhost:8787); the server will append/v1automatically and log a one-line diagnostic to stderr confirming the normalization.
Related MCP server: synapse-mcp
Status
Wave 2 done (2026-05-22): 4 tools fully wired to @nexusm/sdk (context_retrieve / memory_search / memory_create / memory_feedback) + full §M-3 HTTP→MCP error mapping (mapHttpStatusToMcpError + 2 new error codes Unauthorized/RateLimited) + Prometheus metrics with cardinality guard + cross-substory + E2E + schema_sync integration tests. Correction (2026-09-12, issue #32): that mapping only recognised axios-shaped errors, which @nexusm/sdk never throws, so until the mapSdkErrorToMcpError bridge landed every SDK failure reached clients as InternalError (-32603); an auth edge / proxy answering instead of Nexus (SDK 5.2.0 UpstreamInterceptError) now maps to Unauthorized (-32011) with data.upstream_intercept: true — see CHANGELOG [Unreleased]. Wave 3 (nexus-claude-plugin Anthropic marketplace) pending — see proposal.
Known Wave 2 limitations: (1) CI red until Gate-1 — @nexusm/sdk@1.3.0 npm publish pending (user action; SDK rename merged at 1fbdd69 in nexus-sdk-js main); (2) integration tests env-gated (require NEXUS_TEST_API_URL/TOKEN/TENANT_ID Forgejo secrets, currently dormant); (3) Python backend mcp.py metrics defined but emit-site wiring deferred to Wave 3 (FU-MCP-BACKEND-EMIT-WIRING); (4) HTTP transport per-request server.connect() is scaffold-only — Wave 3 entry condition (FU-MCP-HTTP-SESSION) before plugin TASK-019 E2E runs.
Available Tools
4 toolsnexus.context_retrieveA
Use when user asks anything that might need context from prior sessions, prior conversations, or stored facts. Single call returns relevant memories, recent conversation turns, and knowledge entities together. Prefer this over nexus.memory_search when query is open-ended.
Inputs: user_id (required), query (required), limit, as_of. Returns: retrieve_id, memories, conversation_turns, knowledge_entities, +2 more
nexus.memory_createA
Persist a new memory. Use when user explicitly asks to 'remember X' or when storing structured facts (preferences, decisions, code snippets with language tag). Set memory_type to 'episodic' for events, 'semantic' for facts, 'procedural' for how-tos.
Inputs: user_id (required), content (required), memory_type, metadata, +3 more. Returns: memory_id, created_at, conflict_resolution
nexus.memory_feedbackA
Submit per-memory feedback on a previous nexus.context_retrieve call. Pass retrieve_id from earlier output. Rating 1-5, plus per-memory useful flag with optional reason. v5 feedback loop drives quality_score reranking.
Inputs: user_id (required), retrieve_id (required), rating (required), item_feedback, +2 more. Returns: feedback_id, retrieve_id, status, created_at
nexus.memory_searchA
Targeted semantic search over memories. Use when query has specific keyword/topic and user wants list of memories (no need for conversation/knowledge layers). For Chinese queries, mode='hybrid' falls back to trigram word_similarity.
Inputs: user_id (required), query (required), limit, mode, +2 more. Returns: memories, total
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: context_retrieve for broad context, memory_create for storing, memory_feedback for feedback, memory_search for targeted search. No overlap.
All tools follow nexus_verb_noun pattern with snake_case. Slight inconsistency: two use 'memory_' prefix, one uses 'context_', but this reflects functional difference.
Four tools cover core memory operations perfectly: creation, two retrieval modes, and feedback. No redundancy, each tool earns its place.
CRUD surface is incomplete: update and delete for memories are missing. Feedback partially addresses quality improvement, but lifecycle management has gaps.
Maintenance
Related MCP Connectors
Remote MCP server exposing SMI Aware tools, resources, and skills over Streamable HTTP.
Remote MCP server exposing your Node Command fleet (files, shell, processes, browser) to AI hosts.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Remote MCP server for supportsheep: run AI interviews and manage support content for your blog.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceMCP server that wraps the nexus CLI, giving AI agents cross-session memory, semantic search, preference learning, and smart context injection.61 npmMIT
- AlicenseNot gradedqualityDmaintenanceMCP server for the Synapse ecosystem that exposes the Synapse Memory API, Browser Proxy, and SSH Proxy as MCP tools, enabling multi-tenant, stateful interactions via stdio or HTTP/SSE.1MIT
- FlicenseNot gradedqualityBmaintenanceModel Context Protocol server for MCPGRAM that enables MCP clients to interact with connectors like GitHub, Slack, and Notion through stdio or Streamable HTTP transports.-

orca-mcpofficial
AlicenseNot gradedqualityCmaintenanceExternal MCP server for controlling Orca worktrees, agent sessions, and multi-agent orchestration from any MCP client via stdio or Streamable HTTP.30 npm3MIT