Recall (sakebomb) MCP Server
mcp-recall
npm
v1.14.1
Source verified
Published by sakebomb — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
Context compression and persistent retrieval for Claude Code
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 6 = 94. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 4
high Dynamic code execution in server code (plugins/mcp-recall/dist/server.js)MTC-SRC-001
In the server's implementation (`plugins/mcp-recall/dist/server.js:2892`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const makeValidate = new Function(`${names_1.default.self}`, `${names_1.default.scope}`, sourceCode); const val
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server plugins/mcp-recall/dist/server.js
high Shell/command execution in server code (plugins/mcp-recall/dist/cli.js)MTC-SRC-002
In the server's implementation (`plugins/mcp-recall/dist/cli.js:5169`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ort { spawnSync } from "child_process"; import { resolve } from "path"; var pathCache = new Map; function getProjectKey(
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server plugins/mcp-recall/dist/cli.js
high Shell/command execution in server code (plugins/mcp-recall/dist/server.js)MTC-SRC-002
In the server's implementation (`plugins/mcp-recall/dist/server.js:19542`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ort { spawnSync } from "child_process"; import { resolve } from "path"; var pathCache = new Map; function getProjectKey(
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server plugins/mcp-recall/dist/server.js
high Shell/command execution in server code (src/project-key.ts)MTC-SRC-002
In the server's implementation (`src/project-key.ts:2`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ort { spawnSync } from "child_process"; import { resolve } from "path"; const pathCache = new Map<string, string>(); /
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/project-key.ts
Tools 11
Each tool and what it can reach — statically extracted from the published source.
recall__list_storedingests untrusted inputrecall__contextno sensitive capabilityrecall__exportno sensitive capabilityrecall__forgetno sensitive capabilityrecall__noteno sensitive capabilityrecall__pinno sensitive capabilityrecall__retrieveno sensitive capabilityrecall__searchno sensitive capabilityrecall__session_summaryno sensitive capabilityrecall__statsno sensitive capability
Show 1 more tool ↓
recall__suggestno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (11 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 7
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v1.14.1 latest |
A 94/100 | 4 | 1.13.0 | 2026-09-07 |
v1.14.0 |
A 94/100 | 4 | 1.13.0 | 2026-09-05 |
v1.13.0 |
A 94/100 | 4 | 1.12.1 | 2026-08-20 |
v1.12.0 |
A 94/100 | 4 | 1.12.1 | 2026-08-10 |
v1.10.1 |
A 94/100 | 4 | 1.12.1 | 2026-08-02 |
Show 2 more versions ↓
v1.9.0 |
A 94/100 | 4 | 1.12.1 | 2026-07-28 |
v1.7.0 |
A 90/100 | 2 | 1.8.0 | 2026-07-23 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan mcp-recall --onlineOther implementations of Recall 4
Independent packages implementing the same tool, scanned with the same engine. Compare all 5 side by side →
Shared persistent memory for Claude Code, Gemini CLI, Cursor, and any MCP-aware AI client. Local-first, brain-swappable.
MCP server for Recall — self-hosted AI memory system. Gives Claude access to recall_store, recall_search, recall_get, recall_timeline, recall_rehydrate, recall_health, and recall_profile_proposals.
Persistent cross-session memory for Claude and AI agents. Self-host on Redis/Valkey, or use the managed cloud at recallmcp.com.
Recall MCP server - Team memory for AI coding tools
More in AI, Memory & Reasoning
FDA device & vehicle recall risk for AI agents: recall history, MAUDE trend, risk score.
Open-source MCP server exposing Agent402.Tools' catalog — 500+ strong: 400+ self-hostable tools + 100 multi-tool skill packs (security-audit, trend-analysis, structured-scrape, decode-blob, forecasting-bake-off) for AI agents — browser, web search & answe
Zero-dependency MCP server that gives AI agents a self-updating project memory in AGENTS.md. Returns merge instructions instead of mutating state, so every change is a reviewable diff.
MCP Apps UI resources and server helpers for n8n
MCP server providing comprehensive access to BookStack knowledge management system
MCP server for tracking achievements with STAR methodology