abstract_toolserver
The abstract_* ecosystem exposed as an API-callable AI toolset — every tool
is a plain Python function turned into a self-describing HTTP endpoint by
abstract_flask. A portable
tool layer any model (Claude, hugpy, …) can drive over HTTP instead of being
bound to one runtime's tool harness.
Run it
pip install abstract_toolserver # + the extras you want to expose
python -m abstract_toolserver # HOST/PORT/DEBUG from TOOLSERVER_* env
from abstract_toolserver import get_toolserver_app
app = get_toolserver_app() # a normal Flask/WSGI app
Self-describing surface
The app auto-mounts introspection endpoints (from abstract_flask):
| Endpoint | What it gives an LLM |
|---|---|
GET /prefixes |
the tool categories (/fs, /db, /ui, …) |
GET /endpoints |
every tool as {endpoint, url, methods} |
GET /<cat>/<tool>?help=true |
that tool's signature/help |
Call a tool with JSON; unknown keys are pruned to the function signature, and the
reply is {"result": ...} (or {"error": ...}). Discover-and-dispatch from a
client is already provided by abstract_apis.make_endpoint_call.
curl -s localhost:5000/fs/count_tokens -d '{"text":"hello world"}'
# {"result": 2}
curl -s localhost:5000/db/schema # {"result": {table: [cols...]}}
curl -s 'localhost:5000/db/query?help=true'
Tool categories
| Prefix | Tools | Backend |
|---|---|---|
/fs |
search, read_span, extract, read_file, write_file, read_json, find_keys, find_paths, glob, imports, find_content | abstract_search, abstract_utilities, abstract_paths |
/text |
count_tokens, chunk, detect_language | abstract_utilities |
/web |
text, links, attributes | abstract_webtools |
/media |
ocr_image, pdf_text, summarize, keywords, transcribe | abstract_ocr, abstract_pandas, media_intelligence |
/ai |
query | abstract_ai |
/db |
tables, schema, columns, fetch, query | abstract_database |
/sys |
run_cmd | stdlib (gated) |
/ui |
capture, monitors, ocr, windows, click_verify | abstract_clicks, abstract_windows |
/loci |
list, pointers (the hugpy-station distribution feed), register, archive | central locus registry (Postgres) |
/handoff |
request, list, claim, station (seat-API probe) | jump-in seats via hugpy-station |
/session |
identity, pull, spin, list, release | pull a live Claude Code session into a hugpy-station seat |
Safety gates
Backends load lazily, so the server boots on a headless box and a missing backend errors only when its tool is called. Beyond that:
/db/query— read-only gate: rejects anything that isn't a singleSELECT/WITH, blocks stacked statements and data-modifying keywords. Use/db/fetch(identifier-composed, params-not-SQL) as the default read path./sys/run_cmd— disabled unlessTOOLSERVER_CMD_ALLOWLIST=ls,grep,…is set; only allowlisted binaries run./fs/read_file·/fs/write_file— local-only; the underlying SSH/remote kwargs are never exposed at the boundary./session/pull— the agent's own MCP bridge (abstract-claude mcp) fills the calling session's identity (session id, user@host, cwd); the toolserver registers machine + session loci, records apullhandoff, and asks the station (HANDOFF_SPAWN_URL) to seatclaude --resume <id> --fork-sessionthere. Without a resume-capable station it stays pending (/session/spinretries) — never a silent fresh seat./ui/click_verify— the click→observe→verify loop: locate (text or image template) → click → re-capture → report whether the screen (or aregion) changed. The half most tool APIs lack.
Configuration
| Env var | Purpose |
|---|---|
TOOLSERVER_HOST / TOOLSERVER_PORT / TOOLSERVER_DEBUG |
bind + debug |
TOOLSERVER_CMD_ALLOWLIST |
comma-separated binaries /sys/run_cmd may run |
SOLCATCHER_POSTGRESQL_* |
DB connection (via abstract_database) |
HANDOFF_SPAWN_URL / HANDOFF_SPAWN_TOKEN |
hugpy-station seat API (/api/handoff/spawn) + its X-Console-Token |
1 maintainer
Metadata
1 maintainer
Release files for abstract-toolserver 0.0.24
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| abstract_toolserver-0.0.24.tar.gz | 58.1 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| abstract_toolserver-0.0.24-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 113.8 kB
Release files / abstract_toolserver-0.0.24.tar.gz
| Download URL | abstract_toolserver-0.0.24.tar.gz |
|---|---|
| Size | 58.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
863a1d4c69b5d5c4b1b88c83ccc40c6f467e9662264ca485102824fd03277d76
|
|
BLAKE2b-256 checksum How to use checksums |
8783df486bb1dcb7f761c8d5f447d6d5422a72e560b512fc59e2b8b984528390
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.12
|
Release files / abstract_toolserver-0.0.24-py3-none-any.whl
| Download URL | abstract_toolserver-0.0.24-py3-none-any.whl |
|---|---|
| Size | 55.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
cec6aea04cdbc3d68832957491290447af5abc10f5b1ee5985b25cb73fa675b7
|
|
BLAKE2b-256 checksum How to use checksums |
3d73d28b948f265af553ca7ac7dbd95f176584ff1d8671c7fd5b2d101ff2b4b2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.12
|
