Memgrep MCP Server
memgrep
npm
v1.6.7
Published by darula-hpp — 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.
Local agent memory, coding loop, Cursor from Telegram, scheduled playbooks, and MCP tools.
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 − 7 = 93. 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 13
high Reads a sensitive credential path or dumps the environment (dist/loop/git.js)MTC-SRC-006
In the server's implementation (`dist/loop/git.js:17`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: redentials.*|.*secret.*|id_rsa.*|.*\.(?:pem|p12|pfx|key))$/i; const ENV_EXAMPLE_RE = /(?:^|\/)\.env(?:\..+)?\.example$/i
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/loop/git.js
high Reads a sensitive credential path or dumps the environment (dist/swe1/git.js)MTC-SRC-006
In the server's implementation (`dist/swe1/git.js:17`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: redentials.*|.*secret.*|id_rsa.*|.*\.(?:pem|p12|pfx|key))$/i; const ENV_EXAMPLE_RE = /(?:^|\/)\.env(?:\..+)?\.example$/i
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/swe1/git.js
high Shell/command execution in server code (dist/clipboard.js)MTC-SRC-002
In the server's implementation (`dist/clipboard.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: rt { spawn } from 'node:child_process'; import { platform } from 'node:os'; function clipboardCommand() { switch (pl
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/clipboard.js
high Shell/command execution in server code (dist/edge/launchd.js)MTC-SRC-002
In the server's implementation (`dist/edge/launchd.js:4`): 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 { defaultHome } from '../memory/store.js'; import { buildLaunchdPlist, la
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/edge/launchd.js
high Shell/command execution in server code (dist/edge/local-tools.js)MTC-SRC-002
In the server's implementation (`dist/edge/local-tools.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: rt { spawn } from 'node:child_process'; import path from 'node:path'; const TOOL_DESCRIPTIONS = { edge_ping: 'Ping t
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/edge/local-tools.js
high Shell/command execution in server code (dist/edge/service.js)MTC-SRC-002
In the server's implementation (`dist/edge/service.js:11`): 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 { defaultHome } from '../memory/store.js'; import { resolveMemgrepProgram
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/edge/service.js
high Shell/command execution in server code (dist/ingest/launchd.js)MTC-SRC-002
In the server's implementation (`dist/ingest/launchd.js:4`): 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 { defaultHome } from '../memory/store.js'; import { buildLaunchdPlist, la
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/ingest/launchd.js
high Shell/command execution in server code (dist/jobs/launchd.js)MTC-SRC-002
In the server's implementation (`dist/jobs/launchd.js:4`): 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 { defaultHome } from '../memory/store.js'; import { buildLaunchdPlist, la
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/jobs/launchd.js
high Shell/command execution in server code (dist/loop/background.js)MTC-SRC-002
In the server's implementation (`dist/loop/background.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: rt { spawn } from 'node:child_process'; import { closeSync, writeFileSync } 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 dist/loop/background.js
high Shell/command execution in server code (dist/loop/git.js)MTC-SRC-002
In the server's implementation (`dist/loop/git.js:4`): 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: { execFile } from 'node:child_process'; import { promisify } from 'node:util'; import { createPullRequest, defaultGhRunn
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/loop/git.js
high Shell/command execution in server code (dist/loop/pr.js)MTC-SRC-002
In the server's implementation (`dist/loop/pr.js:4`): 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: { execFile } from 'node:child_process'; import { promisify } from 'node:util'; const execFileAsync = promisify(execFile)
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/loop/pr.js
medium Untrusted input can drive an external actionMTC-FLOW-005
Untrusted-input tools ([get_chat, jira_get_issue, ph_get_post, neon_connection_uri]) co-exist with external-action tools ([jira_create_issue]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.
Evidence: untrusted [get_chat, jira_get_issue, ph_get_post, neon_connection_uri] → sinks [jira_create_issue]
Fix: Require confirmation for state-changing/egress actions triggered after processing untrusted content.
Location: flow get_chat → jira_create_issue
low Shell/command execution in packaging/dev tooling (dist/docs/pdf.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/docs/pdf.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: rt { spawn } from 'node:child_process'; import { existsSync, mkdtempSync, readFileSync, rmSync, } from 'node:fs'; import
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/docs/pdf.js
Tools 64
Each tool and what it can reach — statically extracted from the published source.
get_chatingests untrusted inputjira_create_issuenetwork egressjira_get_issueingests untrusted inputneon_connection_uriingests untrusted inputph_get_postingests untrusted inputcursor_runno sensitive capabilitycursor_statusno sensitive capabilitycursor_workspacesno sensitive capabilitydocs_extractno sensitive capabilitydocs_fillno sensitive capability
Show 54 more tools ↓
docs_listno sensitive capabilitydocs_list_templatesno sensitive capabilitydocs_serveno sensitive capabilitydocs_setupno sensitive capabilityedge_cursor_runno sensitive capabilityedge_loop_runno sensitive capabilityedge_pingno sensitive capabilityedge_runno sensitive capabilityedge_statusno sensitive capabilitygcloud_get_instanceno sensitive capabilitygcloud_list_instancesno sensitive capabilitygcloud_list_projectsno sensitive capabilitygcloud_logs_queryno sensitive capabilityjira_add_commentno sensitive capabilityjira_list_projectsno sensitive capabilityjira_searchno sensitive capabilityjira_transitionno sensitive capabilityjobs_addno sensitive capabilityjobs_listno sensitive capabilityjobs_logsno sensitive capabilityjobs_removeno sensitive capabilityjobs_runno sensitive capabilityjobs_updateno sensitive capabilitylist_chatsno sensitive capabilityloop_remove_actionno sensitive capabilityloop_remove_exitno sensitive capabilityloop_remove_inputno sensitive capabilityloop_runno sensitive capabilityloop_run_statusno sensitive capabilityloop_statusno sensitive capabilityloop_upsert_actionno sensitive capabilityloop_upsert_exitno sensitive capabilityloop_upsert_inputno sensitive capabilityneon_get_projectno sensitive capabilityneon_list_branchesno sensitive capabilityneon_list_projectsno sensitive capabilityph_commentsno sensitive capabilityph_searchno sensitive capabilityph_todayno sensitive capabilityposthog_feature_flagsno sensitive capabilityposthog_get_flagno sensitive capabilityposthog_queryno sensitive capabilityposthog_top_eventsno sensitive capabilityrecallno sensitive capabilityrememberno sensitive capabilityresolve_openno sensitive capabilityupstash_dbsizeno sensitive capabilityupstash_delno sensitive capabilityupstash_getno sensitive capabilityupstash_pingno sensitive capabilityupstash_scanno sensitive capabilityupstash_setno sensitive capabilityupstash_ttlno sensitive capabilityupstash_typeno sensitive capability
Toxic flows 1
Cross-tool combinations that form a data-exfiltration primitive (untrusted input → sensitive source → external sink).
What this scan could not see
- Tools were statically extracted from the published source (64 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 |
|---|---|---|---|---|
v1.6.7 latest |
A 93/100 | 13 | 1.13.0 | 2026-09-07 |
v1.6.6 |
A 93/100 | 13 | 1.12.1 | 2026-08-03 |
v1.6.4 |
A 100/100 | 12 | 1.5.0 | 2026-07-22 |
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 memgrep --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