Recalld (EU)
Server Details
Hosted long-term memory for AI agents via MCP. Recalld updates facts as information changes and retrieves relevant context. Connect with a Recalld EU account.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- OAuth
- Works in Glama
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 4 tools
memory_recall and memory_search are the closest pair, but the descriptions clearly separate them (LLM-synthesized answer vs. raw embedding matches), and memory_filters is explicitly framed as a prerequisite helper for the other two. No two tools appear to do the same thing, though the recall/search distinction requires reading past the names.
All four tools share a consistent snake_case `memory_` prefix, making the server's scope immediately obvious. The only minor deviation is `memory_filters`, a plural noun rather than a verb, but it reads naturally as a listing operation.
Four tools is on the lean side but well matched to a narrow memory-retrieval domain: write, filtered lookup, semantic recall, and metadata discovery. Nothing feels redundant or padded, though the surface is thin enough that any missing operation is noticeable.
The read path is well covered (filters, search, recall) and ingestion exists via memory_add, but there is no way to update, delete, or forget a memory, and no operation to fetch a specific stored fact by id. Agents that need to correct bad memories or clean up stale data will hit a dead end.
Available Tools
4 toolsmemory_addAInspect
Ingest content into memory (conversation or document inputs). Agent is fixed by the OAuth connection.
Inputs: inputs (required), task_id, thread_id.
memory_filtersAInspect
List the source kinds, authors and document paths this agent holds. Call it before passing source_kind, author or path to memory_recall or memory_search, so the filter matches something.
Inputs: thread_id.
memory_recallBInspect
Recall relevant facts for a query using LLM-assisted selection. Returns a concise answer from stored memory.
Inputs: query (required), path, limit, scope, +5 more.
memory_searchBInspect
Search memory using embedding retrieval without LLM selection. Returns multiple matching facts for the agent to digest.
Inputs: query (required), path, limit, scope, +5 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Hosted long-term memory for AI agents via MCP. Recalld updates facts as information changes and retrieves relevant context. Connect with a Recalld US account.
Hosted memory for AI agents over MCP. One memory shared by all your agents.
Hosted agent memory: store, search, and recall facts across sessions from any MCP client.
Persistent memory, knowledge graph, task management and more for AI agents via MCP.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to store and semantically retrieve durable memories across sessions via MCP or REST, with tools for remembering, recalling, asking, updating, and forgetting memories.17 npmMIT
- AlicenseAqualityDmaintenancePersistent memory API for AI agents — store, recall, and inject semantically-searchable context across sessions. EU-hosted, GDPR-compliant. Supports Claude, Cursor, Cline, and any MCP-compatible client.42MIT
- AlicenseAqualityDmaintenancePersistent memory for AI agents. Store, recall, and share knowledge across sessions with five MCP tools: remember, recall, context, forget, and share. Includes semantic search and agent/user/org scoping.53Apache 2.0
- AlicenseNot gradedqualityDmaintenancePersistent memory for AI agents. Store and semantically search memories via REST API or MCP. Free tier available.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.