rlm-mcp-server (wgthomas/rlm-mcp-server) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 8 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
C
Emerging
74/100

rlm-mcp-server

Provides recursive language model capabilities to AI assistants, enabling efficient exploration of large contexts through iterative Python code execution.

→ wgthomas/rlm-mcp-server· listed on glama

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

Code Verified⚡ Live Monitored: not connected

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

wgthomas

Source: Glama

Is this your MCP?

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 →

⚡ Connect GitHub for Live Monitored

Install from

Glamanot scored here

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.

// key findings
✅
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
🔐
You'll be asked for 2 credentials: RLM_API_KEY, OPENAI_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes8 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

rlm_load_context

Load a large context into an RLM session for programmatic exploration. USE THIS WHEN: You have a document, codebase, or dataset too large to analyze directly in your context window. RLM lets you explore it by writing Python code (searching, parsing, counting, extracting). WORKFLOW: 1. Call rlm_load_…

rlm_load_file

Load a file into an RLM session. Args: file_path: Path to the file to load context_name: Variable name to use in the REPL (default: CONTEXT) description: Optional description of what this file contains Returns: Session info including session_id to use for queries

rlm_list_sessions

List all active RLM sessions. Returns: List of session info dictionaries

rlm_close_session

Close and remove an RLM session to free memory. Args: session_id: The session ID to close Returns: Status message

rlm_query

Ask a question about loaded context - RLM explores it programmatically. HOW IT WORKS: Instead of reading the whole document, RLM iteratively writes Python code to search/parse/analyze the content until it can answer your question. This allows analyzing content far larger than any context window. PRE…

rlm_quick_query

One-shot RLM: load content and ask a question in a single call. USE THIS FOR: Quick analysis when you only have one question about the content. Automatically cleans up the session afterward. USE rlm_load_context + rlm_query INSTEAD when: - User might ask follow-up questions about the same content - …

rlm_execute_code

Execute Python code directly against a loaded context. This is for power users who want to explore the context manually without the LLM loop. The code has access to CONTEXT (or whatever the context_name is) as a variable. Available in REPL: - CONTEXT (or your context_name): the loaded text - re: reg…

rlm_config

Get current RLM server configuration. Returns: Current configuration settings

// 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.
configRLM_MODELPrimary model for RLM
configRLM_SUB_MODELModel for iterations (can be cheaper)
configRLM_MAX_ITERATIONSMax exploration iterations
configRLM_API_BASEAPI endpoint (for local models)
🔐 secretRLM_API_KEYAPI key
🔐 secretOPENAI_API_KEYAPI key
// 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

8/8 tools missing one or more hints — rlm_load_context (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); rlm_load_file (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); rlm_list_sessions (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +5 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.

License file

No license file

Add a LICENSE file (MIT, Apache-2.0, etc.).

Tool test coverage

Only 2/8 tools referenced in tests (25%)

Write tests that reference each tool by name so every tool has at least one test.

Secrets not logged

5 secret values sent to print

Redact or omit secret values from log output.

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.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 5 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Score](https://m8ven.ai/badge/mcp/wgthomas/rlm-mcp-server)](https://m8ven.ai/mcp/wgthomas/rlm-mcp-server)
Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.
commit: 2f6529885c5d834774765b0c3bd7ed998312ca26
code hash: 2008babddfc8c5d8da39fc14173f41104964c1f5b40e386ab26d0c7e853cf590
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