mcp server
agent-recall
Correction-first agent memory. Precision KPI tracks if agents heed warnings. 5 layers, local-only.
Description as published by the maintainer. Source
- version 3.4.31
- active
- memory and context
active — Most recent push to the repository was 2026-08-04. Dashed tags are derived by ZBS Index from the published description, not stated by the maintainer.
What this server can do
5 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.
check(goal, delta, prior, outcome, project, evidence, posterior, confidence, assumptions, decision_id, understanding, human_correction)- Use when the user asks to validate understanding, verify alignment, or check if their interpretation matches the human's intent.
recall(limit, query, since, project, feedback)- Use when the user asks to recall, search, find, or look up previous memory, context, or decisions. Required: query.
remember(content, context, project)- Use when the user asks to remember, store, note, or save a specific decision, fact, or insight. Required: content.
session_end(project, summary, insights, open_phase, trajectory, close_phase)- Use when the user asks to save, checkpoint, summarize, end, retain, or persist the current session. Optionally pass close_phase / open_phase to update the project pipeline narrative spine in the same call. Required: summary.
session_start(mode, context, project, verbose)- Use when the user asks to start, load, continue, resume, or open memory for a project. Set mode='lite' for a ≤500-token briefing (good for fresh conversations where the agent will pull memory on demand via recall/memory_query/skill_recall).
Last successful function declaration observed on
.
Source: pkg:npm/agent-recall-mcp. We list what the server declared;
we do not call any of these functions.
Endpoint status observed on
.
Source: pkg:npm/agent-recall-mcp.
Signals
These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.
| Signal | Value | What it measures | Window | Observed | Source |
|---|---|---|---|---|---|
| GitHub stars | 364 | Number of GitHub accounts that bookmarked this repository since it was created. It is a bookmark count, not installs, not active users and not quality. | cumulative, all time | GitHub | |
| Last commit | 2026-08-04 | Date of the most recent push to any branch. This is the strongest cheap indicator of whether the project is still maintained. | point in time | GitHub | |
| Open issues | 28 | Open issues plus open pull requests, as GitHub counts them together. A high number can mean an active project or an abandoned one. | as of fetch | GitHub | |
| Latest published version | 3.4.31 | Latest version string the maintainer published to the registry. | as of fetch | Model Context Protocol | |
| Registry record last updated | 2026-06-20 | When the registry record was last updated by its maintainer. | point in time | Model Context Protocol | |
| License | MIT | Licence GitHub detected in the repository. Detection can be wrong; the LICENSE file is authoritative. | as of fetch | GitHub | |
| First listed in the MCP Registry | 2026-06-20 | Date this server was first published to the official MCP Registry. Not a usage or quality measure. | point in time | Model Context Protocol | |
| repository status | active | The repository exists on GitHub and is not archived. This says nothing about how recently it was worked on. | as of fetch | GitHub | |
| mcp tools declared | 5 tools | Number of functions the server declared when started and asked to list them. It says what the server offers an agent, not how well any of it works. | as of probe | npm |
|
| mcp endpoint status | ok | The server listed 5 functions when asked. | as of probe | npm |
|
| package install scripts | none | This package declares no install-time scripts, so installing it does not execute any of its code. | as of probe | npm |
Where to get it
Related, by what their authors tagged them
-
io.github.aayoawoyemi/ori-memory
— last commit 2026-07-30, shares agent-memory, persistent-memory
Persistent memory infrastructure for AI agents. Identity, knowledge graph, and search.
-
Zikkaron
— last commit 2026-04-01, shares agent-memory, persistent-memory
Biologically-inspired persistent memory engine for Claude Code MCP agents
-
Talamus
— last commit 2026-08-05, shares agent-memory, persistent-memory
Local-first, source-grounded memory that survives AI agent sessions.
-
io.github.archetypal-ai/archetypal-ai
— last commit 2026-03-24, shares agent-memory, persistent-memory
Persistent memory for AI agents. recall, remember, checkpoint — soul preservation.
-
io.github.camgitt/memoir
— last commit 2026-08-06, shares agent-memory, persistent-memory
Persistent memory for AI coding tools via MCP. Remembers across sessions and machines.
-
io.github.davidmosiah/delx-memory
— last commit 2026-08-06, shares agent-memory, persistent-memory
Local-first persistent memory MCP: shared SQLite key/value store, searchable, TTL-aware, secret-safe
-
com.memxus/memxus
— last commit 2026-07-30, shares persistent-memory
Persistent memory layer that saves and recalls your project context and preferences.
-
coldstart
— last commit 2026-08-06, shares persistent-memory
Codebase memory for AI agents: an AST index plus agent-written notes that self-stale.
-
io.github.alfredoizdev/contextforge-mcp
— last commit 2026-07-23, shares persistent-memory
Persistent memory MCP server for Claude Code, Cursor, and GitHub Copilot.
-
io.github.annibale-x/mcp-memento
— last commit 2026-04-01, shares persistent-memory
An MCP server that provides persistent memory and context management across sessions
These share tags the maintainers applied themselves, such as agent-memory, persistent-memory. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.
This is not a recommendation and not a test result. It is a map of what the authors said their work is about.
Also from goldentrii
-
io.github.Goldentrii/proxy-veil
— last commit 2026-04-10
Residential proxy MCP server for AI agents — geo-targeting, sticky sessions, anti-bot bypass.
How the author describes it
Topics the maintainer set on GitHub: agent-learning, agent-memory, ai-memory-systems, claude-code, claude-mcp, correction-tracking, mcp-server, memory-palace, persistent-memory, typescript.
This record as data
Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.
GET /api/v1/entries/mcp_server.json