mirror of
https://github.com/mims-harvard/ToolUniverse.git
synced 2026-09-19 07:31:47 +08:00
Shanghua Gao
4ae46d0b83
* feat: improve tool descriptions for better discoverability - search_clinical_trials: rewrite description to lead with disease/drug search use cases and example queries, making it clearly discoverable for natural language searches like "find clinical trials for a drug" - gwas_search_associations: rewrite description to emphasize keyword search capability with example traits, distinguishing from ID-lookup tools - gwas_get_variants_for_trait: expand description with disease examples and clarify this finds all variants for a trait - Add 14 tests validating description quality and search/ID tool distinction * feat: improve GWAS SNP tool descriptions for discoverability - gwas_search_snps: expand description with rs ID and gene name examples - gwas_get_snps_for_gene: add gene name examples and clarify use case * fix: ChEMBL drug search redirect and Orphanet gene lookup subtype fallback - ChEMBL: pref_name__contains now triggers /drug.json → /molecule.json redirect (previously only query/q params did) - Orphanet: _get_genes() now tries direct orphacode lookup first, then searches subtypes by disease name when parent code lacks gene entries (e.g., Marfan syndrome 558 → finds FBN1 via subtype 284963) - Added tests for both fixes * fix: Orphanet search flooding, EuropePMC HTML abstracts, PubChem discoverability - Orphanet search_diseases: add limit param (default 20) to prevent 3400+ result flooding; return count/total_count metadata - EuropePMC: strip HTML tags from abstractText field - PubChem: improve PubChem_get_CID_by_compound_name description for better search discoverability - Added tests for all fixes * refactor: extract helpers in Orphanet _get_genes for clarity Extract _fetch_genes_for_code() and _find_subtype_codes() to reduce nesting and eliminate duplication in the gene lookup strategies. * fix: GTEx gene symbol auto-resolution and ClinVar condition quoting - GTEx: add gene_symbol parameter that auto-resolves to versioned GENCODE ID via /reference/gene API (e.g., FBN1 -> ENSG00000166147.13) - GTEx: unversioned Ensembl IDs also auto-resolved to versioned form - ClinVar: quote multi-word conditions for phrase matching - Integration test: increase timeout to 180s for compose workflow * refactor: reorder GTEx helpers for readability (define before use) * fix: version bump to 1.1.2 and correct CLI docs - Bump version to 1.1.2 in pyproject.toml and server.json - Fix tu_cli.rst: trim verbose examples, fix --detail flag, remove inaccurate "all commands" claim for output flags - Fix cli_tools.rst: correct --field choices, default host/port/workers, remove non-existent doctor flags, fix alias descriptions - Fix toolspace.rst: tu serve does not accept --load/--global/--workspace - Fix skill docs: tu find is keyword scoring not AI-powered, add missing custom mode, tu serve --load → tooluniverse --load
121 lines
2.6 KiB
ReStructuredText
121 lines
2.6 KiB
ReStructuredText
tu — ToolUniverse CLI
|
|
=====================
|
|
|
|
``tu`` is the command-line interface for ToolUniverse. It mirrors the compact-mode MCP tools so you can discover and call tools directly from your shell.
|
|
|
|
.. code-block:: bash
|
|
|
|
tu <command> [options]
|
|
|
|
Output is human-readable by default. Add ``--json`` for pretty JSON or ``--raw`` for compact JSON (pipe-friendly).
|
|
|
|
---
|
|
|
|
Commands
|
|
--------
|
|
|
|
list
|
|
~~~~
|
|
|
|
List available tools. Default view shows category counts; add ``--categories`` to list tools within a category.
|
|
|
|
.. code-block:: bash
|
|
|
|
tu list # category overview
|
|
tu list --categories uniprot # tools in a category
|
|
tu list --mode basic --limit 20 # names + descriptions
|
|
tu list --mode custom --fields name type category
|
|
|
|
Modes: ``names``, ``categories`` (default), ``basic``, ``by_category``, ``summary``, ``custom``
|
|
|
|
grep
|
|
~~~~
|
|
|
|
Search tools by text or regex.
|
|
|
|
.. code-block:: bash
|
|
|
|
tu grep protein # substring search in names
|
|
tu grep protein --field description
|
|
tu grep '^UniProt' --mode regex
|
|
|
|
Fields: ``name`` (default), ``description``, ``type``, ``category``
|
|
|
|
find
|
|
~~~~
|
|
|
|
Find tools by natural-language query (keyword scoring, no API key needed).
|
|
|
|
.. code-block:: bash
|
|
|
|
tu find 'protein structure analysis'
|
|
tu find 'search for drug targets' --limit 5
|
|
tu find 'gene expression' --categories GTEx ENCODE
|
|
|
|
info
|
|
~~~~
|
|
|
|
Show the schema for one or more tools.
|
|
|
|
.. code-block:: bash
|
|
|
|
tu info UniProt_get_entry_by_accession
|
|
tu info UniProt_get_entry_by_accession --detail brief
|
|
tu info UniProt_get_entry_by_accession ChEMBL_get_molecule
|
|
|
|
run
|
|
~~~
|
|
|
|
Execute a tool. Arguments can be ``key=value`` pairs or a JSON string.
|
|
|
|
.. code-block:: bash
|
|
|
|
tu run UniProt_get_entry_by_accession accession=P12345
|
|
tu run list_tools '{"mode": "categories"}'
|
|
|
|
test
|
|
~~~~
|
|
|
|
Test a tool with example inputs and report pass/fail.
|
|
|
|
.. code-block:: bash
|
|
|
|
tu test Dryad_search_datasets # use built-in example inputs
|
|
tu test MyAPI_search '{"q": "test"}' # custom input
|
|
|
|
status
|
|
~~~~~~
|
|
|
|
Show how many tools are loaded and the top categories.
|
|
|
|
.. code-block:: bash
|
|
|
|
tu status
|
|
|
|
build
|
|
~~~~~
|
|
|
|
Regenerate the static tool registry and coding-API wrapper files. Output defaults to ``.tooluniverse/coding_api/``; use ``--output`` to override.
|
|
|
|
.. code-block:: bash
|
|
|
|
tu build
|
|
tu build --output ./my_tools
|
|
|
|
serve
|
|
~~~~~
|
|
|
|
Start the MCP stdio server (equivalent to running ``tooluniverse``).
|
|
|
|
.. code-block:: bash
|
|
|
|
tu serve
|
|
|
|
---
|
|
|
|
See Also
|
|
--------
|
|
|
|
- :doc:`toolspace` — configure which tools load via ``profile.yaml``
|
|
- :doc:`building_ai_scientists/compact_mode` — compact mode in MCP
|