Ori Memory MCP Server
ori-memory
npm
v0.6.1
Published by aayoawoyemi — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
Cognitive architecture for persistent AI agent memory. Knowledge graph with learning retrieval, ACT-R decay, and spreading activation. Markdown-native, local-first, zero cloud. MCP server + CLI.
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 − 6.3 = 94. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −6.3 | Untrusted input concatenated into a command sink MTC-SRC-009 | injection |
2. Client adoption risk — 94 − 7 = 87. 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 |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
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 9
high Shell/command execution in server code (adapters/claude-code/hooks/capture.mjs)MTC-SRC-002
In the server's implementation (`adapters/claude-code/hooks/capture.mjs: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: spawnSync } from "node:child_process"; import { existsSync, readFileSync } from "node:fs"; import path from "node:pat
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 adapters/claude-code/hooks/capture.mjs
high Shell/command execution in server code (adapters/claude-code/hooks/orient.mjs)MTC-SRC-002
In the server's implementation (`adapters/claude-code/hooks/orient.mjs: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: spawnSync } from "node:child_process"; import { existsSync, readdirSync } from "node:fs"; import path from "node:path
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 adapters/claude-code/hooks/orient.mjs
high Shell/command execution in server code (adapters/claude-code/hooks/validate.mjs)MTC-SRC-002
In the server's implementation (`adapters/claude-code/hooks/validate.mjs: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: spawnSync } from "node:child_process"; import { existsSync, readFileSync } from "node:fs"; import path from "node:pat
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 adapters/claude-code/hooks/validate.mjs
high Shell/command execution in server code (adapters/hermes/plugin/hooks.py)MTC-SRC-002
In the server's implementation (`adapters/hermes/plugin/hooks.py:37`): 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: try: result = subprocess.run( ["ori", "health"], capture_output=True, text
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 adapters/hermes/plugin/hooks.py
high Shell/command execution in server code (adapters/opencode/plugin/lifecycle.js)MTC-SRC-002
In the server's implementation (`adapters/opencode/plugin/lifecycle.js:15`): 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: spawnSync } from "node:child_process"; import path from "node:path"; const LOG_ROOT = process.env.APPDATA || proces
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 adapters/opencode/plugin/lifecycle.js
high Shell/command execution in server code (dist/cli/repl.js)MTC-SRC-002
In the server's implementation (`dist/cli/repl.js:5`): 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: ecFileSync } from "node:child_process"; import readline from "node:readline"; import chalk from "chalk"; import { getVer
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 dist/cli/repl.js
high Shell/command execution in server code (dist/core/llm.js)MTC-SRC-002
In the server's implementation (`dist/core/llm.js:1`): 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: { execSync } from "node:child_process"; export const DEFAULT_LLM_CONFIG = { provider: null, model: null, api
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 dist/core/llm.js
medium Hardcoded egress to an external endpoint (dist/providers/anthropic.js)MTC-SRC-003
In the server's implementation (`dist/providers/anthropic.js:42`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. 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 response = await fetch("https://api.anthropic.com/v1/messages", { method: "POST",
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 dist/providers/anthropic.js
medium Untrusted input concatenated into a command sink (dist/cli/repl.js)MTC-SRC-009
In the server's implementation (`dist/cli/repl.js:57`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: h aries-cli execSync(`npx tsx "${ariesEntry}"`, { stdio: "inherit", cwd: sta
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 dist/cli/repl.js
Tools 19
Each tool and what it can reach — statically extracted from the published source.
ori_addno sensitive capabilityori_exploreno sensitive capabilityori_explore_concludeno sensitive capabilityori_explore_expandno sensitive capabilityori_explore_startno sensitive capabilityori_healthno sensitive capabilityori_index_buildno sensitive capabilityori_orientno sensitive capabilityori_promoteno sensitive capabilityori_pruneno sensitive capability
Show 9 more tools ↓
ori_queryno sensitive capabilityori_query_fadingno sensitive capabilityori_query_importantno sensitive capabilityori_query_rankedno sensitive capabilityori_query_similarno sensitive capabilityori_statusno sensitive capabilityori_updateno sensitive capabilityori_validateno sensitive capabilityori_warmthno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (19 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 3
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 |
|---|---|---|---|---|
v0.6.1 latest |
B 87/100 | 9 | 1.13.0 | 2026-09-07 |
v0.6.0 |
B 87/100 | 9 | 1.12.1 | 2026-07-28 |
v0.5.5 |
A 93/100 | 6 | 1.12.1 | 2026-07-27 |
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 ori-memory --onlineMore 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