cleveragents-core/tools/mcp_graphify_server.py

#!/usr/bin/env python3
"""MCP server wrapping the local graphify code-knowledge-graph CLI.

Spawned by OpenCode via ``.opencode/opencode.json``'s ``mcp`` block
and exposed to agents that have ``mcp__graphify*: allow`` in their
permission block.

Replaces the v2 ``.opencode/plugins/graphify.js`` reminder plugin
(which broke deny-by-default bash allowlists by prepending
``echo "..." && `` to every command — see the plugin file's header
comment for the post-mortem) and the per-agent boilerplate that
allowed ``"graphify *"`` and granted ``external_directory`` read
access to ``graphify-out/``. Agents now need a single permission
line — ``"mcp__graphify*": allow`` — to use the graph.

Tools exposed
-------------

``report(head_lines: int = 200)``
    Return the first ``head_lines`` lines of ``GRAPH_REPORT.md`` (god
    nodes + community structure + cross-module summary). The default
    matches the historical ``cat … | head -200`` pattern that the
    task-implementor used to run on every session.

``query(question: str, budget: int = 2000)``
    BFS traversal of the graph for a natural-language question.
    Returns ``graphify``'s text output verbatim — typically node
    citations with file:line references, ranked by graph distance.

``path(a: str, b: str)``
    Shortest path between two concept nodes (e.g. between
    ``SessionContext`` and ``post_session_action``).

``explain(concept: str)``
    Neighborhood summary for a single node.

State
-----

Stateless. Every call re-reads ``graphify-out/graph.json`` — which
``graphify update`` (run by the user / git commit hook) rewrites on
code changes. No caching here; the underlying CLI is fast and the
graph is small.

Configuration
-------------

``GRAPHIFY_OUT_DIR`` (default
``/home/drew/repos/cleveragents-core/graphify-out``)
    Where ``graph.json`` and ``GRAPH_REPORT.md`` live.

``GRAPHIFY_BIN`` (default ``graphify`` on PATH)
    The graphify CLI binary. Override if multiple installs exist.

``GRAPHIFY_TIMEOUT_S`` (default ``30``)
    Per-call subprocess timeout in seconds. ``query`` and ``path``
    can take a few seconds on larger graphs; the default leaves
    headroom without letting a hung CLI stall a worker session.
"""

from __future__ import annotations

import os
import shutil
import subprocess
import sys
from pathlib import Path

from mcp.server.fastmcp import FastMCP

sys.path.insert(0, str(Path(__file__).parent))
from _mcp_common import make_main  # noqa: E402

# ─── Configuration ─────────────────────────────────────────────────
GRAPHIFY_OUT = Path(
    os.environ.get(
        "GRAPHIFY_OUT_DIR",
        "/home/drew/repos/cleveragents-core/graphify-out",
    )
)
GRAPHIFY_BIN = os.environ.get("GRAPHIFY_BIN", "graphify")
GRAPHIFY_TIMEOUT_S = int(os.environ.get("GRAPHIFY_TIMEOUT_S", "30"))

GRAPH_JSON = GRAPHIFY_OUT / "graph.json"
GRAPH_REPORT = GRAPHIFY_OUT / "GRAPH_REPORT.md"


# ─── Server ────────────────────────────────────────────────────────
server = FastMCP("graphify")


def _check_environment() -> str | None:
    """Return a human-readable error string if the environment is not
    usable, or ``None`` if everything is in place. Called at the top
    of every tool so the agent gets a clear, actionable message
    instead of an opaque subprocess failure.
    """
    if not GRAPHIFY_OUT.is_dir():
        return (
            f"graphify-out directory not found at {GRAPHIFY_OUT}. "
            "Set GRAPHIFY_OUT_DIR or run `graphify update <repo>` to generate it."
        )
    if not GRAPH_JSON.is_file():
        return (
            f"graph.json not found at {GRAPH_JSON}. "
            "Run `graphify update <repo>` to (re-)generate the graph."
        )
    if shutil.which(GRAPHIFY_BIN) is None and not Path(GRAPHIFY_BIN).is_file():
        return (
            f"graphify CLI not found (looked for {GRAPHIFY_BIN!r}). "
            "Set GRAPHIFY_BIN or install with `uv tool install graphifyy`."
        )
    return None


def _run_graphify(args: list[str]) -> str:
    """Invoke the graphify CLI and return its stdout. On non-zero
    exit or timeout, returns a formatted error string the agent can
    read directly — never raises through MCP, so a single misuse
    doesn't crash the server."""
    cmd = [GRAPHIFY_BIN, *args]
    try:
        result = subprocess.run(
            cmd,
            capture_output=True,
            text=True,
            timeout=GRAPHIFY_TIMEOUT_S,
            check=False,
        )
    except subprocess.TimeoutExpired:
        return (
            f"ERROR: graphify timed out after {GRAPHIFY_TIMEOUT_S}s. "
            f"Command: {' '.join(cmd)!r}"
        )
    except FileNotFoundError:
        return (
            f"ERROR: graphify binary not found at {GRAPHIFY_BIN!r}. "
            "Set GRAPHIFY_BIN env var or install graphify."
        )
    if result.returncode != 0:
        return (
            f"ERROR: graphify exited {result.returncode}. "
            f"stderr: {result.stderr.strip()[:500]}"
        )
    return result.stdout


@server.tool()
def report(head_lines: int = 200) -> str:
    """First N lines of GRAPH_REPORT.md (god nodes, communities,
    surprising cross-module connections). Call this once per session
    to orient before grep/find — the report tells you the shape of
    the codebase. Default 200 lines matches the historical
    ``cat … | head -200`` pattern.
    """
    env_err = _check_environment()
    if env_err is not None:
        return f"ERROR: {env_err}"
    if not GRAPH_REPORT.is_file():
        return (
            f"ERROR: GRAPH_REPORT.md not found at {GRAPH_REPORT}. "
            "Run `graphify update <repo>` to regenerate it."
        )
    try:
        with GRAPH_REPORT.open("r", encoding="utf-8") as fh:
            lines = [next(fh) for _ in range(max(1, head_lines))]
    except StopIteration:
        # File is shorter than head_lines — fall through with what we have.
        pass
    except OSError as exc:
        return f"ERROR: reading {GRAPH_REPORT}: {exc}"
    return "".join(lines)


@server.tool()
def query(question: str, budget: int = 2000) -> str:
    """BFS traversal of the graph for a natural-language question.
    Returns ranked node citations with file:line references, capped
    at ``budget`` tokens. Use this **instead of** ``grep -r`` for
    cross-module questions ("how does X relate to Y", "what depends
    on Z", "what's downstream of file F"). Default budget 2000 is
    the same default the CLI uses.
    """
    env_err = _check_environment()
    if env_err is not None:
        return f"ERROR: {env_err}"
    if not question.strip():
        return "ERROR: question must be non-empty"
    return _run_graphify(
        [
            "query",
            question,
            "--graph",
            str(GRAPH_JSON),
            "--budget",
            str(max(1, int(budget))),
        ]
    )


@server.tool()
def path(a: str, b: str) -> str:
    """Shortest path between two concept nodes in the graph. Use
    when you need to understand the dependency chain between two
    specific things (e.g. ``path("SessionContext",
    "post_session_action")``).
    """
    env_err = _check_environment()
    if env_err is not None:
        return f"ERROR: {env_err}"
    if not a.strip() or not b.strip():
        return "ERROR: both `a` and `b` must be non-empty"
    return _run_graphify(["path", a, b, "--graph", str(GRAPH_JSON)])


@server.tool()
def explain(concept: str) -> str:
    """Plain-language neighborhood summary for a single concept node
    (its direct neighbors, types of edges, file:line citations). Use
    when you've located a node and want to understand what's around
    it before reading source.
    """
    env_err = _check_environment()
    if env_err is not None:
        return f"ERROR: {env_err}"
    if not concept.strip():
        return "ERROR: concept must be non-empty"
    return _run_graphify(["explain", concept, "--graph", str(GRAPH_JSON)])


# No startup fail-fast on missing graphify-out: the operator may
# spawn OpenCode before running the first ``graphify update``, and
# :func:`_check_environment` gives a clearer in-band error than a
# startup crash.
main = make_main(server, "mcp_graphify_server")


if __name__ == "__main__":
    sys.exit(main())