context-mode
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.
Warning. Serious findings were identified. Review the full report before connecting. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
mksglu
Source: Glama · also listed on github_topic, github_repo_search
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
When Vitest UI server is listening, arbitrary file can be read and executed
esbuild allows arbitrary file read when running the development server on Windows
BUN_INSTALLCLAUDE_CODE_HEADLESSCLAUDE_CONFIG_DIRCLAUDE_PLUGIN_ROOTCLAUDE_PROJECT_DIRCLAUDE_SESSION_IDCODEX_HOME[mcp_servers.context-mode] block or $/hooks.json is needed whenCODEX_PROJECT_DIRCONTEXT_MODE_AGY_EXEC_TIMEOUT_MSCONTEXT_MODE_DEBUGCONTEXT_MODE_EMBEDDED_PLUGIN_TOOLSCONTEXT_MODE_HOOK_STDIN_IDLE_MSCONTEXT_MODE_MCP_SENTINEL_DIRCONTEXT_MODE_PLATFORMCONTEXT_MODE_PROJECT_DIRCONTEXT_MODE_REQUIRE_SECURITYCONTEXT_MODE_SECURITY_BUNDLE_PATHCONTEXT_MODE_SESSION_SUFFIXCONTEXT_MODE_SUPPRESS_SECURITY_WARNINGCOPILOT_HOMEPrerequisites: Node.js >= 22.5 (or Bun), GitHub Copilot CLI (copilot) installed. Set first if you use an isolated Copilot home.CTX_FETCH_STRICTCTX_TEST_PLATFORMCTX_TEST_PROC_DIRCURSOR_CWDCURSOR_SESSION_IDCURSOR_TRACE_IDGEMINI_PROJECT_DIRIDEA_HOMEIDEA_INITIAL_DIRECTORYJETBRAINS_CLIENT_IDKIMI_CODE_HOMEKIMI_PROJECT_DIRNO_COLOROPENCLAW_PROJECT_DIROPENCLAW_STATE_DIRThe installer uses $ from your environment (default: /openclaw). To specify a custom path:OPENCODE_PROJECT_DIRPI_CODING_AGENT_DIRPI_CONTEXT_MODE_MODEL_IDPI_CONTEXT_MODE_PRICE_OUTPUT_PER_TOKENQWEN_SESSION_IDSHELLVITESTVITEST_WORKER_IDVSCODE_CWDVSCODE_PIDXDG_CONFIG_HOMETool annotations match behaviour
3 read-only tools perform write/delete/exec — ctx_search (line 517: unlinkSync(filePath)); ctx_stats (line 517: unlinkSync(filePath)); ctx_doctor (line 92: spawnSync("cmd.exe", ["/d", "/s", "/c", "codex plugin list"], {)
Either remove the readOnlyHint:true annotation, or remove the write/delete call from the tool handler.
Destructive tools are labelled
7 tools perform destructive updates without destructiveHint — ctx_index deletes at line 874 (unlinkSync(rp)); ctx_search deletes at line 517 (unlinkSync(filePath)); ctx_fetch_and_index deletes at line 874 (unlinkSync(rp))
Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.
Tool inputs are validated
10/11 tool handlers declare input schemas (91%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Shell command execution
51 child_process calls — runs shell commands
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Readable source code
2 files appear obfuscated
Ship unminified, readable source.
No arbitrary install scripts
Has postinstall/preinstall script — runs arbitrary code on npm install
Remove postinstall/preinstall hooks unless they’re essential.
Dev dependencies
1 critical/high in dev-only deps (does not ship to users)
Upgrade dev dependencies when convenient.
Dependency freshness
2/8 production deps stale: turndown-plugin-gfm@2022-05-22 (4.2y), @mixmark-io/domino@2024-04-08 (2.3y)
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/mksglu/context-mode)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check