# CLI reference Generated from the command-line help at build time. ## `mcparser` ```text Usage: mcparser [OPTIONS] COMMAND [ARGS]... LLM agents for dependency parsing with CoNLL-U files. ╭─ Options ────────────────────────────────────────────────────────────────────╮ │ --version Show the version and exit. │ │ --install-completion Install completion for the current shell. │ │ --show-completion Show completion for the current shell, to copy │ │ it or customize the installation. │ │ --help Show this message and exit. │ ╰──────────────────────────────────────────────────────────────────────────────╯ ╭─ Commands ───────────────────────────────────────────────────────────────────╮ │ validate Validate a CoNLL-U file. Exits with status 1 if there are errors. │ │ run Score and refine a prediction file with the agents, over several │ │ rounds. │ │ score Only run the scorer: give every changed or unscored cell a │ │ confidence. │ │ init Create a prediction file from raw text or a gold CoNLL-U file, │ │ then apply the frequency baseline. │ │ evaluate Compare predictions with gold annotation (the CoNLL 2018 metrics: │ │ precision, recall and F1). │ │ settings Print the settings (defaults, or CONFIG with defaults filled in) │ │ as YAML. │ │ mcp The CoNLL-U MCP server. │ ╰──────────────────────────────────────────────────────────────────────────────╯ ``` ## `mcparser init` ```text Usage: mcparser init [OPTIONS] {INPUT} Create a prediction file from raw text or a gold CoNLL-U file, then apply the frequency baseline. ╭─ Arguments ──────────────────────────────────────────────────────────────────╮ │ * INPUT Text (one sentence per line), YAML with 'text' │ │ fields, or CoNLL-U (annotation is removed, │ │ segmentation kept). │ │ [required] │ ╰──────────────────────────────────────────────────────────────────────────────╯ ╭─ Options ────────────────────────────────────────────────────────────────────╮ │ * --output -o CoNLL-U file to │ │ create. │ │ [required] │ │ --source -s Trusted example │ │ sources, │ │ [NAME=]PATH[:ro[… │ │ Repeatable. │ │ --baseline --no-baseline Fill in what the │ │ trusted sources │ │ make obvious (no │ │ LLM). │ │ [default: │ │ baseline] │ │ --force Overwrite OUTPUT │ │ and its │ │ review/history │ │ files. │ │ --max-sentences Only use the │ │ [x>=1] first N sentences │ │ (after any │ │ --sentence │ │ filter). │ │ --skip Skip the first N │ │ [x>=0] sentences of │ │ INPUT (e.g. to │ │ start a new │ │ batch). │ │ [default: 0] │ │ --help Show this message │ │ and exit. │ ╰──────────────────────────────────────────────────────────────────────────────╯ ``` ## `mcparser run` ```text Usage: mcparser run [OPTIONS] {prediction} Score and refine a prediction file with the agents, over several rounds. ╭─ Arguments ──────────────────────────────────────────────────────────────────╮ │ * prediction Prediction CoNLL-U file (edited in place). │ │ [required] │ ╰──────────────────────────────────────────────────────────────────────────────╯ ╭─ Options ────────────────────────────────────────────────────────────────────╮ │ --source -s Trusted example │ │ sources, │ │ [NAME=]PATH[:ro[… │ │ Repeatable. │ │ --corpus [NAME=]PATH[,PAT… │ │ unannotated text │ │ (one sentence or │ │ paragraph per │ │ line) that agents │ │ can search for │ │ how a word is │ │ used. Repeatable. │ │ --config -c Settings YAML │ │ (see `mcparser │ │ settings`). │ │ --model One model for │ │ every role │ │ (overrides │ │ --strong-model │ │ and │ │ --efficient-mode… │ │ --strong-model Model for the │ │ demanding roles │ │ (default │ │ anthropic:claude… │ │ --efficient-mod… Cheaper model for │ │ the │ │ --efficient-roles │ │ (default │ │ anthropic:claude… │ │ --light-model Cheapest model, │ │ for the │ │ --light-roles │ │ (default │ │ anthropic:claude… │ │ --efficient-rol… Comma-separated │ │ roles that use │ │ the efficient │ │ model (default │ │ upos,feats,score… │ │ --light-roles Comma-separated │ │ roles that use │ │ the light model │ │ (default xpos). │ │ --strong-thinki… Reasoning for │ │ strong roles: │ │ off, on, minimal, │ │ low, medium, │ │ high, xhigh │ │ (default: the │ │ model's own). │ │ --efficient-thi… Reasoning for │ │ efficient roles │ │ (same values as │ │ --strong-thinkin… │ │ --light-thinking Reasoning for │ │ light roles (same │ │ values as │ │ --strong-thinkin… │ │ --batch-sentenc… Maximum sentences │ │ [x>=1] per agent task │ │ (default 8). │ │ --model-for ROLE=MODEL │ │ override, e.g. │ │ lemma=anthropic:… │ │ --roles Comma-separated │ │ roles to run: │ │ segmentation, │ │ upos, xpos, │ │ lemma, feats, │ │ syntax, head, │ │ deprel, deps. │ │ --rounds Maximum rounds. │ │ [x>=1] │ │ --joint-syntax --separate-synt… One agent sets │ │ HEAD and DEPREL │ │ together │ │ (default), or │ │ separate head and │ │ deprel agents. │ │ --final-score --no-final-score Re-score the │ │ cells changed in │ │ the last round │ │ (default off). │ │ --max-cost Stop starting │ │ [x>=0.01] agent tasks once │ │ the estimated │ │ cost reaches this │ │ many dollars (run │ │ again to │ │ continue). │ │ --corpus-tool --no-corpus-tool Let agents call │ │ corpus_find │ │ (default) or give │ │ them only the │ │ corpus evidence │ │ in the prompt. │ │ --threshold Refine cells │ │ [0<=x<=1] below this │ │ confidence. │ │ --concurrency Sentences │ │ [x>=1] processed at │ │ once. │ │ --sentence Only work on this │ │ sent_id. │ │ Repeatable. │ │ --max-sentences Only use the │ │ [x>=1] first N sentences │ │ (after any │ │ --sentence │ │ filter). │ │ --report Write the run │ │ report as JSON. │ │ --help Show this message │ │ and exit. │ ╰──────────────────────────────────────────────────────────────────────────────╯ ``` ## `mcparser score` ```text Usage: mcparser score [OPTIONS] {prediction} Only run the scorer: give every changed or unscored cell a confidence. ╭─ Arguments ──────────────────────────────────────────────────────────────────╮ │ * prediction Prediction CoNLL-U file (edited in place). │ │ [required] │ ╰──────────────────────────────────────────────────────────────────────────────╯ ╭─ Options ────────────────────────────────────────────────────────────────────╮ │ --source -s Trusted example sources, │ │ [NAME=]PATH[:ro[:CONFIDEN… │ │ Repeatable. │ │ --corpus [NAME=]PATH[,PATH...]: │ │ unannotated text (one │ │ sentence or paragraph per │ │ line) that agents can │ │ search for how a word is │ │ used. Repeatable. │ │ --config -c Settings YAML (see │ │ `mcparser settings`). │ │ --model One model for every role │ │ (overrides --strong-model │ │ and --efficient-model). │ │ --efficient-model Cheaper model for the │ │ --efficient-roles (default │ │ anthropic:claude-sonnet-5… │ │ --efficient-thinking Reasoning for efficient │ │ roles (same values as │ │ --strong-thinking). │ │ --batch-sentences [x>=1] Maximum sentences per │ │ agent task (default 8). │ │ --model-for ROLE=MODEL override, e.g. │ │ lemma=anthropic:claude-so… │ │ --concurrency [x>=1] Tasks run at once. │ │ --sentence Only work on this sent_id. │ │ Repeatable. │ │ --max-sentences [x>=1] Only use the first N │ │ sentences (after any │ │ --sentence filter). │ │ --report Write the run report as │ │ JSON. │ │ --help Show this message and │ │ exit. │ ╰──────────────────────────────────────────────────────────────────────────────╯ ``` ## `mcparser evaluate` ```text Usage: mcparser evaluate [OPTIONS] {prediction} {gold} Compare predictions with gold annotation (the CoNLL 2018 metrics: precision, recall and F1). ╭─ Arguments ──────────────────────────────────────────────────────────────────╮ │ * prediction Predicted CoNLL-U. [required] │ │ * gold Gold CoNLL-U. [required] │ ╰──────────────────────────────────────────────────────────────────────────────╯ ╭─ Options ────────────────────────────────────────────────────────────────────╮ │ --json Print JSON instead of a table. │ │ --predicted-only Ignore gold sentences that are not in the │ │ predictions. │ │ --annotated-only Only score predicted sentences that have │ │ been parsed (every HEAD set). │ │ --calibration Also show accuracy by recorded confidence │ │ (Conf in MISC). │ │ --strict Also score all features and relation │ │ subtypes (the official metrics ignore them). │ │ --official Also run the official conll18_ud_eval.py at │ │ this path (sentences it would refuse are │ │ repaired first). │ │ --help Show this message and exit. │ ╰──────────────────────────────────────────────────────────────────────────────╯ ``` ## `mcparser validate` ```text Usage: mcparser validate [OPTIONS] {path} Validate a CoNLL-U file. Exits with status 1 if there are errors. ╭─ Arguments ──────────────────────────────────────────────────────────────────╮ │ * path CoNLL-U file to validate. [required] │ ╰──────────────────────────────────────────────────────────────────────────────╯ ╭─ Options ────────────────────────────────────────────────────────────────────╮ │ --source -s Trusted sources whose tagsets flag unseen values. │ │ --limit Maximum issues to print. [default: 100] │ │ --help Show this message and exit. │ ╰──────────────────────────────────────────────────────────────────────────────╯ ``` ## `mcparser settings` ```text Usage: mcparser settings [OPTIONS] Print the settings (defaults, or CONFIG with defaults filled in) as YAML. ╭─ Options ────────────────────────────────────────────────────────────────────╮ │ --config -c Settings YAML (see `mcparser settings`). │ │ --help Show this message and exit. │ ╰──────────────────────────────────────────────────────────────────────────────╯ ``` ## `mcparser mcp serve` ```text Usage: mcparser mcp serve [OPTIONS] Serve CoNLL-U sources over MCP (stdio for Claude Desktop, or streamable HTTP). ╭─ Options ────────────────────────────────────────────────────────────────────╮ │ * --source -s [NAME=]PATH[:ro|rw[:CONFID… │ │ Repeat for several sources. │ │ Default mode is ro. │ │ [required] │ │ --transport MCP transport. │ │ [default: stdio] │ │ --host Host for streamable-http. │ │ [default: 127.0.0.1] │ │ --port Port for streamable-http. │ │ [default: 8000] │ │ --read-only Register only the read-only │ │ tools. │ │ --root-key MISC attribute holding the │ │ word's root. │ │ [default: Root] │ │ --name Server name shown to MCP │ │ clients. │ │ [default: conllu] │ │ --alignment -a NAME=SOURCE_A,SOURCE_B,PAT… │ │ word alignments between two │ │ sources. Repeatable. │ │ --corpus [NAME=]PATH[,PATH...]: │ │ unannotated text (one │ │ sentence or paragraph per │ │ line) that agents can │ │ search for how a word is │ │ used. Repeatable. │ │ --help Show this message and exit. │ ╰──────────────────────────────────────────────────────────────────────────────╯ ``` ## `mcparser mcp config` ```text Usage: mcparser mcp config [OPTIONS] Print the JSON to add to Claude Desktop's claude_desktop_config.json. ╭─ Options ────────────────────────────────────────────────────────────────────╮ │ * --source -s [NAME=]PATH[:ro|rw[:CONFIDENCE]]. Repeat for │ │ several sources. Default mode is ro. │ │ [required] │ │ --read-only Register only the read-only tools. │ │ --root-key MISC attribute holding the word's root. │ │ [default: Root] │ │ --name Server name shown to MCP clients. │ │ [default: conllu] │ │ --alignment -a NAME=SOURCE_A,SOURCE_B,PATH[:ro|rw[:CONFIDEN… │ │ word alignments between two sources. │ │ Repeatable. │ │ --corpus [NAME=]PATH[,PATH...]: unannotated text (one │ │ sentence or paragraph per line) that agents │ │ can search for how a word is used. │ │ Repeatable. │ │ --help Show this message and exit. │ ╰──────────────────────────────────────────────────────────────────────────────╯ ```