Agent Recall Trail MCP server
Private Agent memory and governed shared knowledge.
0 stars
Reviews
Write oneNobody has reviewed Agent Recall Trail yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Agent Recall Trail tools
No tool declarations could be read from the package source. They show once the server is installed.
Public scan report
scanner v0.1.10 · 2026-10-03 · same rubric, same numbers if you re-run it
- –Code scanpackage could not be scannedn/a
- –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 1 days ago15/15
- Maintainer identityregistry namespace matches repository owner6/10
How Agent Recall Trail compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 83/100
- higher than 68% of 4,460 AI and agents servers
Release history: 3 versions in the registry since 2026-09-09, latest 2026-10-02, typically one every 14 days.
Install Agent Recall Trail in Claude Code, Cursor or VS Code
The registry entry has no remote endpoint or installable package.
What the publisher says
From the Agent Recall Trail repository's README, as published. We do not edit it. Read it on GitHub
ART — Agent Recall Trail
ART is a local-first memory and governed-knowledge product for coding agents. Every Agent gets a physically separate private Recall Trail. Stable conclusions become immutable Knowledge Editions that other Agents can retrieve without seeing private source identities or source bodies.
ART 0.3.6 supports Codex and DeepSeek Harness (DSH) over stdio MCP. It is standalone: no AAA adapter, cloud sync, bundled model, or autonomous publication is required.
Product boundary
default-off switch in that page. It creates at most one bounded private Candidate for an admitted turn; it never publishes shared knowledge.
- Private memory belongs to one process-bound Agent identity.
- Shared knowledge contains only committed, reviewed Editions.
- Agents may capture, recall, read, provide feedback, create proposals, and request governance.
- Human governance runs in ART's local page. An explicitly enabled, default-off local delegation policy also permits one unambiguous instruction to approve and publish atomically; these actions are labeled AgentDelegated, never Human.
- Selective Codex automatic memory is controlled by a separate machine-wide,
- Revocation, supersession, archival, and assurance remain human operations.
- Stored content is evidence, never executable instruction or authorization.
Progressive recall
ART exposes one recall API with four explicit retrieval modes: lexical, full_scan, semantic, and hybrid. The default is always lexical. A compact route request can identify relevant private and shared topics before a bounded recall; exact bodies are returned only by read.
- lexical uses local BM25 plus exact, token, Jieba, and CJK-bigram signals.
- full_scan ranks every governance-eligible canonical record. It needs no embedding service and is intended for completeness-sensitive, smaller stores.
- semantic uses only an explicitly configured embedding endpoint and disposable local vector projections.
- hybrid combines lexical and semantic ranks through an owner-configurable, versioned fusion policy. If the optional provider or projection is unavailable, ART returns the unchanged lexical result and reports the fallback.
ART's optional embedding adapter is supplied and operated by the user. ART does not bundle, download, train, select, or make quality claims for a model merely because its endpoint is compatible.
Quick start
cargo build --release --locked
./target/release/art --home /an/explicit/art-home init --confirm
./target/release/art --home /an/explicit/art-home agent create --id codex-primary --host codex
./target/release/art --home /an/explicit/art-home doctor --agent codex-primary --jsonUse Codex integration or DSH integration to start one bound stdio child. Run art --help for the operator CLI.
Install
Download the native archive and SHA256SUMS from the latest release, verify the archive, then run the included installer with the extracted binary:
bash scripts/install.sh --binary /absolute/path/to/art --confirm
art --version
art doctor --agent codex-primary --jsonThe installer keeps executable bytes under ~/.across/bin/art, creates a discovery link at ~/.local/bin/art, and initializes owner-only ART data. It does not edit Codex or DSH configuration. The thin Codex plugin lives under plugin/agent-recall-trail; its MCP child is permanently bound to codex-primary. See operations before migrating or publishing knowledge.
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Agent Recall Trail: common questions
- Is Agent Recall Trail MCP server safe?
- Mostly: it is graded B (83/100). Read the Agent Recall Trail safety report
- Does Agent Recall Trail need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Agent Recall Trail maintained?
- The last commit was 33 days ago (2026-10-02). The latest release is v0.3.7.
- What can I use instead of Agent Recall Trail?
- Servers from other publishers that do the same job: Total Agent Memory MCP server, Basic Memory MCP server and IWE (iwe.md) MCP server.
Alternatives to Agent Recall Trail
Same job from other publishers: the closest match first, then the best rated.
- Total Agent MemoryPersistent local memory for coding agents: temporal knowledge graph, procedural and episodic recallnot reviewedEstablishedA
- Basic MemoryLocal-first knowledge management with bi-directional LLM sync via Markdown files.not reviewedWidely usedB
- IWE (iwe.md)Markdown knowledge base as agent memory. Runs against the notes directory it is started in.not reviewedEstablishedA
- Mnemoverse MemoryHosted agent memory that learns from outcomes, with shared rooms. No key: mcp.mnemoverse.com/mcpnot reviewedEstablishedA
- Agent RecallCorrection-first agent memory. Precision KPI tracks if agents heed warnings. 5 layers, local-only.not reviewedEstablishedA