Memory + context infrastructure for AI agents. LLM Wiki auto-sync, 15 content-aware summarizers, hybrid search (BM25 + vector + optional LLM judge)
Memory + context infrastructure for AI agents. LLM Wiki auto-sync, 15 content-aware summarizers, hybrid search (BM25 + vector + optional LLM judge), entity
Two problems with today's AI tooling that no one has solved together in a single package.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| observe | Store observation with auto-summarization, importance scoring, entity extraction, topic detection |
| recall | Retrieve verbatim content by filter (importance, type, flag, time) |
| search | Hybrid search (BM25 + vector + optional LLM judge) |
| ask | Natural language Q&A over the full memory store |
| timeline | Reverse-chronological observations with importance badges and flags |
| stats | Token economics for current session (raw vs. compressed) |
| save_knowledge | Save a knowledge entry with contradiction detection + temporal validity windows |
| search_knowledge | Search (superseded entries filtered by default) |
| promote_knowledge | Promote to global cross-project store |
| global_search | Search across all projects simultaneously |
| resolve_contradiction | Resolve knowledge conflicts (supersede / merge / keep / archive) |
| merge_suggestions | View cross-project duplicate suggestions |
| graph_query | Traverse entity relationships |
| add_relationship | Link entities with typed relationships |
| graph_neighbors | Find connected entities (configurable depth) |
| temporal_query | Query what was true at a specific point in time |
| time_travel | Compare project state at two arbitrary timestamps |
| explain_decision | Walk evidence chain backward to reconstruct why a decision was made |
| predict_loss | Identify observations at risk of compression/deletion |
| generate_story | Generate PR description, standup update, ADR, or onboarding guide |
| entity_detect | Detect entities in arbitrary text |
| find_tunnels | Find cross-project topic connections |
| wake_up | Token-budgeted context primer for session start |
| restore_session | Restore session from checkpoint |
| handoff_session | Cross-session continuity package |
| agent_register | Register an agent with role and capabilities |
| agent_status | Check all active agents and their claimed resources |
| claim_files | Claim files to prevent parallel-agent conflicts |
| agent_broadcast | Broadcast a finding to all agents in the project |
| configure | Update runtime configuration |
| summarize | Summarize content without storing (one-shot) |
| execute | Run code (JS, TS, Python, Shell, Ruby, Go, Rust, PHP, Perl, R, Elixir) |
| index_content | Index with code-aware chunking |
| search_content | Search indexed chunks |
| import_conversations | Import conversation history |
| browse | Retrieve observations by person, entity, or topic |
| diagnostics | Error log, pipeline stats, storage health |
{
"mcpServers": {
"context-mem": {
"command": "npx",
"args": [
"context-mem",
"serve"
],
"env": {}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.
Chat with your second brain — search, read and write vault notes through the Local REST API.
Enables AI assistants to securely interact with Azure DevOps through a standardized protocol.