jog-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| JOG_MCP_TOKEN | No | Bearer token required when the server is started in HTTP mode (--http). HTTP mode will not start without it, and the token is checked as a bearer token on every request. Not needed when the server is run over stdio. Example: JOG_MCP_TOKEN=$(openssl rand -hex 32) .venv/bin/jog-mcp --http --host 127.0.0.1 --port 8787 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Romanian surveying and cadastre law, full text, kept in this repository. Quote the article you rely on and name its act — people act on these answers in front of a land-registry counter. If the corpus does not cover the question, say so rather than answering from memory of Romanian law. SOME ACTS ARE REPEALED and kept only for files opened before the repeal: a result marked '!!' says so, names what replaced it, and must not be presented as current law — say it is repealed in your first sentence and answer from the replacement.
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_lawA | Search the Romanian surveying-law corpus (cadastre, land registry, construction permits, land fund) and return the matching articles verbatim. Use this for a question about what the law requires. Queries may be in Romanian or Hungarian; diacritics are optional. Returns the article text, its act and its chapter, so the answer can be cited. |
| get_articleA | Return one article of one act verbatim, by number. Use this whenever an article is cited by number ('art. 24 din Regulament'); it is exact and does not depend on search ranking. |
| find_exactA | Find every article that contains a phrase LITERALLY (case and diacritics ignored). Use it for numbers and fixed wording that ranked search cannot see: '15%', '30 de zile', 'servitute de trecere', 'art. 41 alin. (10)'. Returns each match with the text around it; pull the whole article with get_article. |
| outlineA | List the article headings of one act, with its chapters. Use this to find the right article in a long regulation before pulling its text. |
| list_actsA | What the law corpus holds: each act, its size, the consolidation it came from and the date it was last fetched. Check this when an answer needs to state how current the law text is. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| jogi_kerdes | Answer a question about Romanian surveying law using only this corpus, quoting the article it rests on. |
| dosszie_lista | Assemble the required-documents list for a cadastral procedure, each item traced to its article. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| acts_resource |
TDQS
Scored across 5 tools
Each tool occupies a distinct retrieval mode: ranked search, exact fetch by article number, literal phrase match, structural outline, and corpus metadata. The descriptions explicitly state when to prefer one over another (e.g. get_article 'does not depend on search ranking', find_exact for 'fixed wording that ranked search cannot see'), leaving almost no room for misselection.
Four of five names follow a clear verb_noun pattern (search_law, get_article, find_exact, list_acts). 'outline' is a bare noun that breaks the pattern, though its meaning is still unambiguous.
Five tools is tightly scoped to a read-only legal-corpus server, and each one covers a genuinely different retrieval need. Nothing feels redundant or missing at the count level.
The read-only surface covers ranked search, ID lookup, literal search, structural navigation and freshness metadata — the full lifecycle for answering citable legal questions. Minor gaps remain: no way to restrict search to a specific act, and no explicit pagination or result-limit control for large result sets.