Emerging

74/100

4 days ago

truth-constrained-resume-match-evaluator

Item: truth-constrained-resume-match-evaluator
Rating: 74
Author: M8ven

Truth-constrained RAG resume match evaluator with an agentic Resume Coach layer

→ daksh-malhan/truth-constrained-resume-match-evaluator · listed on github_code

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 push why connect →

Who stands behind it

daksh-malhan

Source: github_code

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

GitHub

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.

🔐

You'll be asked for 1 credential: OPENAI_API_KEY

These are read from process.env at runtime. Make sure you trust where they’ll be sent.

// 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.

configVECTOR_STORE_PROVIDER

configEMBEDDING_MODEL

configOLLAMA_EMBEDDING_MODELexport LLM_PROVIDER=ollama EMBEDDING_PROVIDER=ollama =nomic-embed-text:latest

configEMBEDDING_PROVIDERexport LLM_PROVIDER=ollama =ollama OLLAMA_EMBEDDING_MODEL=nomic-embed-text:latest

configMAX_UPLOAD_MB

configENABLE_MOCK_MODE

🔐 secretOPENAI_API_KEY

configOLLAMA_BASE_URLRuntime: Ollama at

configQDRANT_URL

configCOACH_MAX_ITERATIONShandled by the structured fallback (OLLAMA_AGENT_TOOL_MODE=auto).

configAGENT_LLM_PROVIDERexport =ollama OLLAMA_AGENT_MODEL=qwen2.5:7b-instruct

configLLM_PROVIDERexport =ollama EMBEDDING_PROVIDER=ollama OLLAMA_EMBEDDING_MODEL=nomic-embed-text:latest

configOLLAMA_AGENT_MODELexport AGENT_LLM_PROVIDER=ollama =qwen2.5:7b-instruct

configOLLAMA_AGENT_NUM_PREDICT

configOLLAMA_AGENT_TOOL_MODEauto (default) native structured.

configENABLE_MOCK_FALLBACKMock fallback: disabled by default. It exists only for tests or emergency demos when =true.

configENABLE_COMPARISON_NARRATIVE_LLMfalse skips the optional narrative LLM call; deterministic report text still runs.

configOLLAMA_EMBEDDING_FALLBACK_MODELS

configOLLAMA_EMBEDDING_BATCH_SIZE

configENABLE_INFERENCE_MATCH_LLM

configOLLAMA_INFERENCE_MATCH_MODEL

configOLLAMA_INFERENCE_MATCH_TIMEOUT_SECONDS

configOLLAMA_INFERENCE_MATCH_NUM_PREDICT

configOLLAMA_INFERENCE_MATCH_BATCH_TIMEOUT_SECONDS

configOLLAMA_INFERENCE_MATCH_BATCH_NUM_PREDICT

configINFERENCE_MATCH_BATCH_MODEfalse keeps the more reliable per-requirement matcher as the default; set it to true for experimental maximum-speed batches.

configINFERENCE_MATCH_BATCH_SIZE

configINFERENCE_MATCH_MAX_WORKERS

configOLLAMA_JD_CLEANER_MODEL

configOLLAMA_JD_CLEANER_TIMEOUT_SECONDS

configOLLAMA_JD_CLEANER_NUM_PREDICT

configJD_CLEANER_LLM_MODEalways keeps LLM-based JD cleaning on because it materially affects requirement quality.

configJD_CLEANER_MIN_RULE_REQUIREMENTS

configENABLE_JD_CLEANER_LLM

configOLLAMA_LLM_MODELLLM_PROVIDER=ollama =qwen2.5:7b-instruct \

configOLLAMA_LLM_FALLBACK_MODELS

configOLLAMA_LLM_TIMEOUT_SECONDS

configOLLAMA_LLM_NUM_PREDICT

configOLLAMA_USE_MODELFILE_SYSTEM_PROMPTS

configENABLE_VECTOR_STORE_FALLBACK

configOLLAMA_RESUME_CONTEXT_MODEL

configOLLAMA_RESUME_CONTEXT_TIMEOUT_SECONDS

configOLLAMA_RESUME_CONTEXT_NUM_PREDICT

configRESUME_CONTEXT_LLM_MODEauto uses the local LLM only for sparse or ambiguous resume parses.

configRESUME_CONTEXT_MIN_ACTION_ITEMS

configRESUME_CONTEXT_MIN_SKILLS

configENABLE_RESUME_CONTEXT_LLM

configRAG_RETRIEVAL_MAX_WORKERS

configINFERENCE_MATCH_MIN_SIMILARITY

Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.

deployNEXT_PUBLIC_API_BASE

deployDATABASE_URL

// 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

14/14 tools missing one or more hints — parse_resume_pdf (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); extract_resume_facts (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); extract_job_requirements (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +11 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 4/14 tools referenced in tests (29%)

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

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 4 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/daksh-malhan-truth-constrained-resume-match-evaluator-6qo959)](https://m8ven.ai/mcp/daksh-malhan-truth-constrained-resume-match-evaluator-6qo959)

Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.

commit: 5cf847165b3527633d8e9cdd6352adc89c4e4e0b

code hash: 0a5a472b9aa3583a1b9e55f4e1467293dbec0efa07e750dea2bb588c893c2794

verified: 8/16/2026, 9:41:05 PM

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