SkillMapper MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OLLAMA_LLM_MODEL | No | The Ollama generation model used by the agent. The documented setup is llama3.1:8b, but the suite was also verified end to end with qwen2.5:7b by setting OLLAMA_LLM_MODEL=qwen2.5:7b in .env; scores and wording differ between models. | llama3.1:8b |
| LANGSMITH_API_KEY | No | Your key from smith.langchain.com. Only needed when LANGSMITH_TRACING is enabled. | |
| LANGSMITH_PROJECT | No | The LangSmith project used for traces. Only relevant when LANGSMITH_TRACING is enabled. | skillmapper |
| LANGSMITH_TRACING | No | Set to true to enable LangSmith tracing of the agent's LLM calls (langchain_ollama.ChatOllama) and the hybrid retriever. Inert by default: with LANGSMITH_TRACING unset or false, none of this code path runs and there is no dependency on the LangSmith service. | false |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_documentsC | Hybrid (BM25 + dense) search over ingested resume/job-description chunks. |
| retrieve_evidenceC | Retrieve resume evidence supporting a specific job requirement. |
| compare_resume_to_jobA | Run the full resume-vs-job comparison agent (retrieval + LLM compare + retry/escalation). Expect 30s-several minutes on a local 8B model; returns a cached completed result unless force_rerun=True. |
| capture_reviewer_feedbackC | Record a human reviewer's decision on an evaluation. |
| lookup_evaluation_resultB | Look up stored evaluation results by id, or filter by resume/job/status. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
search_documents and retrieve_evidence both retrieve content, which could cause confusion, but the descriptions differentiate them (broad hybrid search vs. targeted evidence for a specific requirement). The other three tools (compare, capture_feedback, lookup) are clearly distinct.
All five tools follow a consistent verb_noun snake_case pattern: search_documents, retrieve_evidence, compare_resume_to_job, capture_reviewer_feedback, lookup_evaluation_result. Verbs are varied but appropriate and readable.
Five tools is reasonably scoped for a resume-vs-job evaluation domain, covering search, targeted retrieval, the full comparison agent, feedback, and result lookup. It is slightly lean but each tool earns its place.
The lifecycle is mostly covered (search, retrieve, compare, capture feedback, lookup results), but there is no ingestion tool despite descriptions referencing 'ingested' chunks, and no update/delete or reviewer-triage operations. These gaps may force agents to look outside the server.