Persistent, evidence-backed code graph for coding agents.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
π‘ Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
A local code knowledge graph for coding agents, shipped as one static binary.
sinter builds a typed, directed graph of a repository's symbols with
tree-sitter and keeps it fresh incrementally. Start in an unfamiliar repository
with sinter map: it returns a bounded structural inventory with module
node/file counts, dependency hubs measured by graph in-degree, documentation
entry points, and graph-health limitations. It does not infer runtime entry
points or domain ownership. Then use the graph for focused work:
sinter affected). Traversal stops at
hubs and names them; test dependents are counted, not listed, unless
asked for.sinter path).sinter impact), plus --expect <symbol> for the unfinished-refactor
check: direct dependents of a symbol the diff did not touch.sinter grep '<regex>' --within 'affected(<sym>)'), replacing the
run-affected-then-grep-the-files pipeline.sinter ask ranks content-bearing
starting points from names, docs, paths, signatures, string literals, and
limited call evidence. Its confidence line reflects the evidence class of
the top hit; --explain adds the ranking-margin bucket and that bucket's
holdout count with a 95% interval (the holdout is 46 cases, so the
interval is wide). The bucket is not a per-result probability; ask is a
navigator, not a semantic answer engine.sinter show turns a selected symbol into a compact
card with its definition (attributes included) and a one-line used-by
tally; --body adds the source (whole when it fits in 60 lines, else up
to the byte budget), --impls the type's impl blocks, and
show @file:line names the enclosing symbol. A span over 8 KB or 200
lines is a black hole no body dump can show: the card outlines it
instead, listing the nested definitions, literal branches and command
literals inside it with their line numbers (--outline forces it).sinter context "<task>" resolves identifiers in
the task against real node names (fuzzy when needed, shown as
term ~> symbol) and seeds from them, returning edit candidates, string
literals and hand-maintained mirrors that mention the task's terms, and
affected tests as runnable commands with the symbol that reached each.
It never abstains while it has hits. Add --workspace <manifest> to rank
candidates across declared member repositories in one packet.sinter assert no-callers <symbol> checks
depth-one call edges in an explicit corpus scope. Its decision is one of
violated, holds_for_indexed_snapshot, or not_proven; it never claims
runtime exhaustiveness. sinter assert deletable <symbol> tallies every
depth-one dependent across all scopes, grouped by scope.sinter cite <symbol> emits a Markdown location
with a stable symbol key. sinter verify-doc <file.md> re-resolves managed
citations and fails on moved, missing, invalid, or identity-free references.--workspace).The design rule underneath everything: evidence or nothing. An edge
exists only when structural, scope, import, or compiler (SCIP) evidence
binds a reference to a definition (workspace manifests may add
operator-declared cross-repo links, and Rust trait impls add labeled
dynamic dispatch fan-out so blast radius survives dyn Trait).
Ambiguity resolves to nothing β "unresolved" is a first-class, counted
outcome, never a guess. Every edge carries its evidence kind, and every
query can filter on it. Be clear about what that buys without a compiler:
syntax-only evidence binds names it can prove by scope and imports and
leaves the rest (receiver calls, re-exports, macros) unresolved, so the
zero-setup graph is a precise subset, not the full graph. sinter scip
closes that gap where a compiler index is available.
Package managers:
All of them put a binary named sinter on PATH. Or the one-liner, no
dependencies (Linux and macOS; verifies the release checksum, installs
to ~/.local/bin):
Windows, in PowerShell (new and less battle-tested; verifies the release
checksum, installs to %LOCALAPPDATA%\sinter\bin):
To verify a manually downloaded release asset against its GitHub build
provenance attestation (requires the gh CLI):
PyPI wheels carry sigstore provenance via Trusted Publishing. Once
installed, sinter update self-updates from GitHub releases.
Or build from source (requires a Rust toolchain):
Agents that only need a usable local graph should create derived state without installing hooks or editing client configuration:
This command only builds or refreshes .sinter/. It is safe to run within a
read-oriented coding flow.
Onboard a repository β builds the graph, installs git hooks, registers agent integration (AGENTS.md block, MCP), and finishes with a doctor report:
Init prints everything it is about to write, grouped by scope, and asks
once before writing any of it (-y skips the prompt; a non-interactive
run prints the plan and proceeds). Every write lands inside the repo β
nothing under ~/.claude is touched unless --global is passed, which
adds the machine-wide skill card and enforcement hooks. Both init and
ensure append .sinter/ to the root .gitignore when the repository is
a git worktree and no existing line covers it.
Repo-local Claude hooks use bounded strict enforcement: the first broad
recursive search in a session is redirected to Sinter, while a retry is
allowed with a fallback-search reminder. Machine-wide hooks installed by
--global remain advisory.
On a terminal, init asks before running compiler indexers (sinter scip)
because those toolchains execute repository build scripts; pass --scip
or --no-scip to answer up front (non-interactive init skips them).
After that, every query self-syncs at the query boundary β when nothing
changed, the sync is a stat-only walk (no file reads, no write
transactions) β and the git hooks refresh eagerly on commit;
sinter build stays available for CI and scripting. Commands also work
from any subdirectory, discovering the graph root the way git does. The
build report distinguishes the heuristic's anchored miss rate from
compiler-relative accuracy. The anchored rate is useful without SCIP but
is not recall: the heuristic can classify a compiler-resolvable reference
as external.
When a SCIP index is present, the report also prints the compiler
cross-check (what share of internally-bound refs agree with the
compiler) and internal recall vs the compiler (how many compiler-bound
refs sinter found without SCIP). Files edited since the index was built
get no SCIP evidence at all β their references fall back to import and
scope resolution rather than being rebound by byte position β so a stale
index never attributes a call to a name that no longer sits on that line.
Files the grammar could only parse partially are counted in one build
line (N parsed partially (M symbols in them; β¦)); sinter doctor --verbose lists them.
Orient before searching so the next query uses the repository's own module and symbol vocabulary:
The map is the first-pass inventory. Use ask next when the target is still a
concept rather than a known symbol.
Ask a question against the graph (output shown for this repository):
No reviews yet β be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/sinter)<a href="https://allmcps.com/mcp/sinter"><img src="https://allmcps.com/api/badge/sinter?style=directory" alt="Sinter on AllMCPs" /></a>