codex-lcm (Mallet-Dev/codex-lcm) is an MCP server listed on the M8ven Trust Index. M8ven has not graded it: we have no way to read this server ourselves. The publisher has proved control of what we score (Verified Publisher). It is connected through the M8ven GitHub App, so the listing is re-checked on every push.

C
Emerging
74/100
3 days ago

codex-lcm

Enables lossless context management for OpenAI Codex CLI by capturing and compressing conversation history in SQLite, with lexical recall via MCP tools.

Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

⚡ Live Monitored

Monitored 0 days · every push re-verified

Who stands behind it

gmail.com (@Mallet-Dev) · Verified Publisher

Source: Glama

Install from

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
🔐
You'll be asked for 2 credentials: CODEX_LCM_API_KEY, OPENAI_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
Are you the publisher? Confirm or correct these findings.
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configCODEX_LCM_CAPTURE_TOOLSSet to 0 to disable tool capture
configCODEX_LCM_TOOL_RESULT_MAX_CHARSSearchable tool-output preview length
configCODEX_LCM_TOOL_INPUT_MAX_CHARSSearchable tool-input preview length
configCODEX_LCM_DB_PATHSQLite database path
configCODEX_LCM_FRESH_TAILNewest raw messages protected from compaction
configCODEX_LCM_LEAF_CHUNK_TOKENSMaximum estimated tokens in a leaf chunk
configCODEX_LCM_LEAF_MIN_FANOUTActive leaf summaries required for condensation
configCODEX_LCM_CONDENSED_MIN_FANOUTActive deeper summaries required for condensation
configCODEX_LCM_MAX_ROUNDSCompaction rounds per worker run
configCODEX_LCM_MAX_SUMMARY_CALLSProvider attempts allowed per session and call window
configCODEX_LCM_SUMMARY_CALL_WINDOW_MSProvider-attempt accounting window
configCODEX_LCM_SUMMARY_TIMEOUT_MSProvider request timeout
configCODEX_LCM_PROGRESS_THRESHOLDMarks a compaction run stalled below this savings ratio
configCODEX_LCM_ADDITIONAL_CONTEXT_LIMITRestore-context budget in estimated tokens
configCODEX_LCM_COMPACTION_MODELLeaf summarization model
configCODEX_LCM_CONDENSATION_MODELCondensation model
🔐 secretCODEX_LCM_API_KEYOptional provider credential
configCODEX_LCM_BASE_URLOptional OpenAI-compatible endpoint
🔐 secretOPENAI_API_KEYOptional provider credential
configOPENAI_BASE_URLOptional OpenAI-compatible endpoint
configCODEX_LCM_COMPACTION_BACKLOGExtra unsummarized messages allowed before Stop starts a worker
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

6/6 tools missing one or more hints — lcm_status (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); lcm_grep (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); lcm_recall (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +3 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

// embed badge in your README
[![M8ven Score](https://m8ven.ai/badge/mcp/mallet-dev-codex-lcm-mxug18)](https://m8ven.ai/mcp/mallet-dev-codex-lcm-mxug18)
Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.
commit: 0d5a449d393da053a4d6432e760d52d71be33aee
code hash: c0840a07efb66d98e3975d64736ae160c5a178f7c9ef2c73e7017ce338a96460
verified: 9/5/2026, 6:53:26 AM
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

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
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client