1. Conduid
  2. RAG
  3. EcoDB
MCP server · RAG

EcoDB

· github.com/josortmel/EcoDB

Collective AI memory for multi-agent teams. 10-stage GAMR search engine, knowledge graph (Apache AGE), document ingestion, 32+ MCP tools.

Unclaimed ai-memoryapache-agebenchmarksdockerfastapiglinerjina-embeddingsknowledge-graphmcpmemory-managementmulti-agentnerpgvectorpostgresqlpythonragsemantic-search
InstallView source
39Low

Scored a month ago · breakdown

About EcoDB

EcoDB is an MCP server in the RAG category: collective AI memory for multi-agent teams. 10-stage GAMR search engine, knowledge graph (Apache AGE), document ingestion, 32+ MCP tools.

Install

From source
git clone https://github.com/josortmel/EcoDB

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Tools (46)

**Documents**No description in manifest

Parameters not published.

**Governance**No description in manifest

Parameters not published.

**Identity**No description in manifest

Parameters not published.

**Knowledge Graph**No description in manifest

Parameters not published.

**Memory**No description in manifest

Parameters not published.

**Metacognition**No description in manifest

Parameters not published.

classify_documentSet document trust tier (0–3)

Parameters not published.

confirm_document_relationConfirm related document pair

Parameters not published.

delete_memorySoft-delete to recycle bin

Parameters not published.

delete_tripleRemove a graph relationship

Parameters not published.

Show all 46 tools
document_statusCheck document processing status

Parameters not published.

fractal_searchDrill-down navigation: enter at the highest abstraction, zoom by id (quarter → month → week → themes → raw memories), optional semantic ranking per scope

Parameters not published.

get_briefingAgent briefing: foresights + tensions + telescopic summary

Parameters not published.

get_graph_vocabularyRead entity dictionary and approved predicates

Parameters not published.

get_progressive_viewProgressive-zoom boot: each layer compresses the previous, closed periods are never re-read. One call loads an agent's whole memory (size-annotated for MCP hosts)

Parameters not published.

get_relevant_contextContext injection — returns formatted context block for LLM consumption

Parameters not published.

get_telescopic_viewLoad an agent's full fractal memory chain (yearly → weekly + last 3 days)

Parameters not published.

graph_statusGraph statistics (nodes, triples, predicates)

Parameters not published.

list_clustersList an agent's clusters by level / status

Parameters not published.

list_documentsList documents with filters

Parameters not published.

load_identityLoad agent identity fragments (ordered narrative)

Parameters not published.

merge_entitiesSoft-merge source entity into target

Parameters not published.

narrate_clusterWrite / update a cluster narrative (owner-only)

Parameters not published.

neighborsGraph neighbors at depth N

Parameters not published.

path_betweenShortest path between two nodes

Parameters not published.

read_clusterRead a cluster's narrative (+ optional members / sources)

Parameters not published.

read_documentRead document metadata and chunks

Parameters not published.

read_memoryRead a memory by UUID

Parameters not published.

register_documentRegister document for ingestion (PDF, DOCX, audio)

Parameters not published.

reindex_documentRe-queue document for processing

Parameters not published.

review_alias_candidateApprove or reject entity alias candidate

Parameters not published.

save_identitySave agent identity (versioned snapshot)

Parameters not published.

save_memoryStore memory with optional image (auto-embeds, auto-extracts entities, auto-links graph)

Parameters not published.

save_tripleAdd relationship to knowledge graph

Parameters not published.

save_triples_batchBatch add triples (max 100)

Parameters not published.

searchGAMR search (10-stage). Text and image queries, cross-modal

Parameters not published.

search_clustersSemantic search over fractal memory clusters (cosine + label BM25)

Parameters not published.

search_in_documentSearch within a specific document's chunks

Parameters not published.

search_nodesFuzzy search nodes by name

Parameters not published.

search_recentRecent memories with filters (agent, tags, date range)

Parameters not published.

seed_dictionaryBulk-add entries to entity dictionary

Parameters not published.

unarchive_memoryRestore from recycle bin

Parameters not published.

undo_mergeRevert a merge operation

Parameters not published.

unlink_documentSoft-delete a document

Parameters not published.

validate_linkValidate entity↔memory link

Parameters not published.

view_imageView image attached to a memory, inline to the LLM

Parameters not published.

Ask AI

✦

Ask AI about EcoDB

Powered by Claude · Grounded in docs

I know everything about EcoDB. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Questions

About EcoDB

How do I install EcoDB?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is EcoDB safe to use with an AI agent?

Its trust score is 39 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is EcoDB still maintained?

Conduid hasn't recorded a commit date for this repository yet. Check the repository directly for recent activity.