MCP.Market

openchronicle-mcp server

by CSOAI-ORG·io.github.CSOAI-ORG/openchronicle-mcp·v3.0.0.dev1·16 stars

Memory database for LLM agents — persistent semantic + keyword memory, project namespacing, served o

A88/100grade A
What users say
No reviews yet
Be the first
Safety scan
A88/100

full report

Adoption
Growing

16 stars31 downloads/wk

Reviews

Write one

Nobody has reviewed openchronicle-mcp yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

openchronicle-mcp tools (17, 5 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • context_recent

    Catch up on prior context for a project: returns recent memory items.

  • health

    Probe the OC server: DB reachability, config status, embedding subsystem.

  • memory_deletewrite action

    Preview or hard-delete a memory item.

  • memory_embed

    Generate embeddings for memories that lack them (or regenerate all).

  • memory_get

    Fetch a single memory by ID.

  • memory_list

    Browse memory items in reverse-chronological order.

  • memory_pin

    Mark a memory as pinned (or unpin it).

  • memory_save

    Persist a memory item that should outlive the current session.

  • memory_search

    Find memory items relevant to a query (hybrid semantic + keyword).

  • memory_stats

    Summarize memory contents: total/pinned counts, breakdowns by tag and source.

  • memory_updatewrite action

    Edit an existing memory's content or tags in place.

  • onboard_git

    Bootstrap project memory from a remote git repo's commit clusters.

  • project_createwrite action

    Create a new project namespace for memories.

  • project_deletewrite action

    Preview or hard-delete a project and all its memories.

  • project_get

    Fetch a single project by id.

  • project_list

    List every project, with id, name, and creation timestamp.

  • project_updatewrite action

    Rename a project or update its metadata.

Public scan report

scanner v0.1.10 · 2026-10-16 · same rubric, same numbers if you re-run it

no findings
  • Code scan95 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 4 days ago15/15
  • Maintainer identitynamespace and repository owner differ; GitHub account older than a year5/10
Overall 88/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How openchronicle-mcp compares

Against every graded SEO MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
88/100
higher than 80% of 769 SEO servers
Tools
17
the typical SEO server has 6
Tools that change things
29%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
16
more than 92% of 405 SEO servers
Downloads a week
31
more than 20% of 170 SEO servers with a package

What its tools let an agent do: 12 read · 5 change

Install openchronicle-mcp in Claude Code, Cursor or VS Code

claude mcp add openchronicle-mcp -- uvx openchronicle-mcp
Add to Cursor

What the publisher says

From the openchronicle-mcp repository's README, as published. We do not edit it. Read it on GitHub

OpenChronicle

<!-- markdownlint-disable MD033 --> <!-- fleet-confidence --> · claude-fable-5 · 2026-08-30 · details <!-- /fleet-confidence --> <!-- markdownlint-enable MD033 -->

A memory database for LLM agents. Persistent semantic + keyword memory, project namespacing, git-onboard, served over HTTP REST and MCP from a single ASGI process. Runs on your hardware.

What it does

and rejected approaches that survive context compression and new conversations. Retrieve them with hybrid full-text and semantic search via Reciprocal Rank Fusion.

  • Persistent memory across sessions. Save decisions, milestones,

for one workstream doesn't leak into another.

  • Project namespacing. Memory is scoped to projects, so context

return summaries ready for memory ingestion. Seeds long-term memory with the WHY behind existing code.

  • Git onboarding. Clone a repo, cluster commits by relatedness,

(/api/v1/*) and the MCP streamable-HTTP transport (/mcp) on the same port. Single container, single port mapping, single healthcheck.

  • One process, two transports. FastAPI hosts both the REST surface

down, search degrades cleanly to FTS5-only and surfaces the degraded state via /api/v1/health and the MCP health tool. Backfill catches up when the provider returns; the static /health endpoint remains a minimal liveness probe.

  • Embedding-failure degradation. When the embedding provider goes

builds include the bounded Prometheus recorder and guarded /metrics endpoint; the released v3.3.0 image does not. Release and enabled collection remain subject to the performance gates. Eligible builds opt in with OCMETRICSENABLED=true; the default stays off. See the metrics configuration and the optional local monitoring runbook.

  • Optional operational metrics (unreleased). Development and benchmark

savepoint atomicity. Re-runs are idempotent. Future schema changes drop in as NNN_.sql files.

  • Schema migration framework. Versioned .sql migrations with

Backup-before-destructive policy: vacuum runs a backup first as part of the same job. Integrity-check failures trigger emergency backups.

  • Atomic online backups. Uses SQLite's online backup API.

What it isn't

Open WebUI, etc. via the MCP server.

  • Not a conversation engine. v3 has no LLM. Use Claude Code, Goose,

is supported but optional — disabled by default for trusted-LAN deployments. See docs/configuration/security_posture.md for the when-to-enable guidance.

  • Not multi-tenant. Single user. Bearer-token auth via OCAPIKEY

to a directory next to it. Cross-device sync isn't built in; a backup-only Dropbox design is documented but not implemented in docs/design/0001-cloud-backup.md.

  • Not a cloud sync layer. The DB lives on your hardware. Backups go

By design.

Install

From source:

pip install -e ".[mcp,openai]"
oc init
oc serve

The default oc serve binds 127.0.0.1:8000. Override with --host/--port or OCAPIHOST/OCAPIPORT.

Docker (single container, NAS-friendly):

docker run --rm \
  -p 8000:8000 \
  -e OC_API_HOST=0.0.0.0 \
  -v $(pwd)/data:/app/data \
  -v $(pwd)/config:/app/config \
  ghcr.io/carldog/openchronicle-mcp:latest

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

openchronicle-mcp: common questions

Is openchronicle-mcp server safe?
Yes, by our scan: it is graded A (88/100). Read the openchronicle-mcp safety report
How do I install openchronicle-mcp?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does openchronicle-mcp need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is openchronicle-mcp maintained?
The last commit was 23 days ago (2026-10-12). The latest release is v3.0.0.dev1.
What can I use instead of openchronicle-mcp?
Servers from other publishers that do the same job: Miru MCP server, bisibility MCP server and Code Context MCP server. Compare all openchronicle-mcp alternatives.
How does openchronicle-mcp compare with other SEO MCP servers?
safety score 88/100 (higher than 80% of 769 SEO servers); tools 17 (the typical SEO server has 6); tools that change things 29% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to openchronicle-mcp

Same job from other publishers: the closest match first, then the best rated.

All openchronicle-mcp alternatives →
  • Miru
    Hybrid semantic and keyword code search for coding agents.
    B
  • bisibility
    Track keyword rankings, research SEO opportunities, and manage bisibility projects with AI agents.
    A
  • Code Context
    Local code search for AI coding agents: hybrid keyword + semantic + SQL over an index in your repo.
    A
  • Local Rag
    Semantic code & doc search with keyword boost. AST code nav, auto HF mirror, local, privacy-first.
    A
  • GenPark Trie Prefix Keyword Matcher
    High-performance in-memory Trie and multi-keyword search engine for prompt routing and entity extrac
    A