Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Fallow

NPM · FALLOW

Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.

Available components

+18 this week 83 Trust /100

Last scanned (15 hours ago)

Scores higher than 73% of npm servers

Category Developer Tools

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 0 of 9 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency100
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to fallow-rs/fallow). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 1 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability71
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 31281 tokens (~601/item across 52 items; 44 tools + 8 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management27
  • Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "check_runtime_coverage" implies "merge" and declares readOnlyHint instead, contradicting what its own name says it does. See how to fix → Fail
  • An AI judge read all 46 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
What we tested

Checks we ran (16)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Nov 26 +1
    • Package version: 3.44.0 → 3.45.0 functional
  • 19 Nov 26 0
    • Package version: 3.43.2 → 3.44.0 functional
  • 18 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Nov 26 +1
    • Stability: 0.07 → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • Capabilities: pass → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
    • Schema quality: 100 → unverified ▼ functional
    • Package version: 3.43.1 → 3.43.2 functional
  • 15 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 14 Nov 26 +1
    • Malware scan: unverified → pass ▲ security
    • Stability: unverified → 0.03 ▲ functional
    • Package version: 3.43.0 → 3.43.1 functional
  • 13 Nov 26 64

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Analysed npm/fallow@3.45.0

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem npm
Reason Verified
Discovered via Registry attestation endpoint
Source repo fallow-rs/fallow
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/fallow-rs/fallow/.github/workflows/release.yml@refs/heads/main
Rekor log index 4021475898
Predicate type SLSA build provenance https://slsa.dev/provenance/v1
Subject digest sha512:2899e538157f6b770361a7e73bcfdda92b440c04503e22f547eeb9250da5f6efabf6c832b7424d35b0cad09d73b195a783eed242fba479a9ee3619f42

Background: How many MCP packages publish verified provenance →

Dependencies 9 packages
Packages resolved 9
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 44 exposed · ~30,711 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
list_suppressions ~432

List active fallow-ignore suppression markers grouped per file with line, kind, level, reason, and a stale cross-reference. Runs `fallow suppressions --format json` and returns the `kind: "suppression-inventory"` envelope verbatim (a `summary` roll-up plus `files[]`); a governance surface for distrusting a clean verdict by seeing what is suppressed, not a gate, so it always exits 0 even when suppressions exist. Scope with `workspace`, `changed_since` (the natural pull-request review scope), or repeated `file` entries. Read-only. It runs a full analysis to populate the inventory, so on large repos raise `FALLOW_TIMEOUT_SECS` above the default 120s if it times out.

NameTypeReqDescription
allow_remote_extendsboolean|null–Allow trusted HTTPS config `extends` for this request. Defaults to false and never grants process-global trust.
changed_sincestring|null–Git ref (e.g. "main", "HEAD~5"). Scopes the inventory to files changed since the ref, the natural pull-request review scope.
configstring|null–Path to a fallow config file.
filearray|null–Only list suppressions in these files. Relative paths resolve against the project root; forwarded as a repeated `--file` flag.
max_output_bytesinteger|null–Byte cap for this call's response. Lowers the server cap (default 1000000); over it the call is REFUSED (`isError`, `exit_code: 2`).
no_cacheboolean|null–Disable the incremental parse cache.
productionboolean|null–Only analyze production code (excludes tests, stories, dev files).
rootstring|null–Project root; defaults to the working directory.
threadsinteger|null–Parser thread count; defaults to CPU cores.
workspacestring|null–Workspace packages to analyze: name or repo-relative path, comma-separated list, globs, `!` negation.

No output schema declared.

No examples provided.

mutation_inspect ~334

Inspect one mutant of a saved `fallow mutation` JSON report (default: the report that the last run saved in the Fallow cache): original and mutated code, covering tests, and the killing test. A source_sha256 mismatch with the current file gives a stale status, not a wrong answer. This tool never runs tests. A report needs the CLI command `fallow mutation`, which executes the project's tests, so ask your host first. On a Rust root, it reads only the cached map of `cargo fallow mutants`.

NameTypeReqDescription
allow_remote_extendsboolean|null–Allow trusted HTTPS config `extends` for this request. Used only without `report`, as for `config`. Defaults to false and never grants process-global trust.
configstring|null–Path to a fallow config file. Used only without `report`, to find the cache directory that holds the report of the last run.
mutant_idstringyesThe `mutant_id` from a mutation plan or report.
packagestring|null–The Cargo package of a Rust workspace with more than one package. Valid only on a Rust workspace.
reportstring|null–Path to a saved `fallow mutation` report or `mutation_plan` output. A relative path resolves against `root`. Without `root`, it resolves against the working directory of the MCP server. Omitted: the…
rootstring|null–Project root; defaults to the working directory.

No output schema declared.

No examples provided.

mutation_plan ~507

Plan mutation testing and return the plan envelope: each mutant's id, position, operator, disposition, and static test files, plus a source_sha256 per file. Scope: changed code by default, or `all`, or `paths`. This tool never runs tests. Running the mutants needs the CLI command `fallow mutation`, which executes the project's tests, so ask your host first. On a Rust root, it runs `cargo fallow mutants --list` for one `package`, by default all of it.

NameTypeReqDescription
allboolean|null–Plan every source file instead of the changed code.
allow_remote_extendsboolean|null–Allow trusted HTTPS config `extends` for this request. Defaults to false and never grants process-global trust.
changed_sincestring|null–Base ref for the default changed-code scope. Omitted: the base is detected as for `audit`.
configstring|null–Path to a fallow config file.
function_scopeboolean|null–Plan every mutant of each function that holds a changed line. Omitted: the `mutation.functionScope` config key, else the changed lines only.
max_mutantsinteger|null–Maximum number of mutants to plan; the rest are `pending`. A run fills the limit with covered mutants, so it can also run a `pending` one.
mutants_per_lineinteger|null–Keep at most this many mutants on each line; the rest are `pending` with the reason `sampled-out`. Omitted: the `mutation.mutantsPerLine` config key, else no limit.
no_cacheboolean|null–Disable the incremental parse cache.
operatorsarray|null–Kebab-case operator names, for example `relational-operator`. Omitted: the `mutation.operators` config key, else the default set. The opt-in operators, such as `block-statement`, run only when named.
packagestring|null–The Cargo package of a Rust workspace with more than one package. Valid only on a Rust workspace, where the plan covers the whole package unless `paths` or `changed_since` is set.
pathsarray|null–Plan only these files or directories, relative to the root.
rootstring|null–Project root; defaults to the working directory.
threadsinteger|null–Parser thread count; defaults to CPU cores.

No output schema declared.

No examples provided.

mutation_tasks ~403

List the open tasks of a saved `fallow mutation` JSON report as one batch (default: the report that the last run saved in the Fallow cache). A task is a survived or no_coverage mutant: a small change to the code that no test detected. Each task has the mutant_id, file, line, function, operator, status, the source lines before and after the change (original_lines, mutated_lines), and the covering test files. After `fallow mutation --record-args values`, a task can have witness; only witness.verdict witness gives a test input (args, original, mutant), and a verdict is never equivalent; see fallow://tools/mutation_tasks. Write tests that pass on the current code and fail on the changed code; one test can cover several tasks, and a task that no input can detect can be skipped. A task whose file changed after the report is stale and has no code. This tool never runs tests. A report needs the CLI command `fallow mutation`, which executes the project's tests, so ask your host first. A Rust root is not supported yet.

NameTypeReqDescription
allow_remote_extendsboolean|null–Allow trusted HTTPS config `extends` for this request. Used only without `report`, as for `config`. Defaults to false and never grants process-global trust.
configstring|null–Path to a fallow config file. Used only without `report`, to find the cache directory that holds the report of the last run.
reportstring|null–Path to a saved `fallow mutation --format json` report. A relative path resolves against `root`. Without `root`, it resolves against the working directory of the MCP server. Omitted: the report that…
rootstring|null–Project root; defaults to the working directory.

No output schema declared.

No examples provided.

project_info ~202

Get project metadata: active framework plugins, discovered source files, and detected entry points. Useful for understanding how fallow sees the project before running analysis. Supports performance tuning (no_cache, threads).

NameTypeReqDescription
allow_remote_extendsboolean|null–Allow trusted HTTPS config `extends` for this request. Defaults to false and never grants process-global trust.
boundariesboolean|null–Include discovered architecture boundary zones in the response.
configstring|null–Path to a fallow config file.
entry_pointsboolean|null–Include entry-point patterns in the response.
filesboolean|null–Include discovered source files in the response.
no_cacheboolean|null–Disable the incremental parse cache.
pluginsboolean|null–Include active framework plugins in the response.
rootstring|null–Project root; defaults to the working directory.
threadsinteger|null–Parser thread count; defaults to CPU cores.

No output schema declared.

No examples provided.

recommend ~355

Recommend a project-tailored fallow config for an agent to author (`fallow recommend --format json`). Read-only: runs project detection (frameworks, workspace layout, tooling) but not the analysis pipeline, and always exits 0. Returns `{detected, proposed_config, decisions[]}`. `detected` is what fallow saw; `proposed_config` is a safe starting config that both validates against config-schema and loads through fallow's real config loader; `decisions[]` has three tiers: `auto` (decided from unambiguous detection and applied silently), `default` (a disclosed, overridable default carrying a quantified `rationale`), and `taste` (a genuinely subjective choice surfaced as an open multiple-choice `question` with 2-4 options and no baked-in recommended answer, per fallow's taste-ownership principle). Framework rules are never uniformly auto-enabled on a heterogeneous monorepo; entry points beyond the obvious fall back to fallow's own defaults rather than a baked-in guess. Zero-config is a valid stop: the proposed config is an optional refinement over already-strong defaults, not a requirement. Pair with `fallow schema` (the capability manifest carrying per-rule default severity + opt-in) for the full cold-start discover -> recommend -> ask-taste -> author sequence. Honors `root`.

NameTypeReqDescription
max_output_bytesinteger|null–Byte cap for this call's response. Lowers the server cap (default 1000000); over it the call is REFUSED (`isError`, `exit_code: 2`).
rootstring|null–Project root for framework, workspace, and tooling detection; defaults to the working directory.

No output schema declared.

No examples provided.

security_candidates ~797

Returns unverified security candidates, not confirmed vulnerabilities. Runs `fallow security --format json` and returns `kind: "security"`, `security_findings`, category, CWE, severity, evidence, structural trace, reachability ranking context, blind-spot counters, and optional unresolved-callee diagnostics for agent verification. `severity` is a review-priority tier, not a verified vulnerability verdict. Each finding also carries an agent-actionable `candidate` record (`source_kind`, the untrusted-input kind as a stable catalogue id or null; a self-contained `sink` with the captured callee and optional `url_shape` for URL candidates; and the `boundary` crossed), an optional `taint_flow` source-to-sink triple (present only when an untrusted source is import-reachable to the sink), a `finding_id` (the SARIF fingerprint), and a `stable_finding_id` that survives line moves, for verdicts. Set `surface: true` to include the top-level `attack_surface` inventory with source-to-sink paths and defensive-boundary verification prompts. Set gate to `new` for changed-line candidates or `newly-reachable` for candidates that became reachable from entry points; `newly-reachable` requires changed_since. There is no `impact` field: deciding exploitability is the agent's job. `reachability.untrusted_source_trace` is module-level context only and does not prove value flow. `reachability.taint_confidence` tiers reachable candidates as `arg-level` or `module-level`; tier from that field rather than evidence prose. Verify trace, reachability context, severity, and evidence before editing code or presenting a finding as a vulnerability. Supports root, config, workspace, changed_since, paths, changed_workspaces, surface, gate, no_cache, and threads. Use paths for the agent edit loop: it forwards to `fallow security --file` and scopes returned candidates to matching finding anchors, trace hops, untrusted-source reachability trace hops, or unresolved-callee diagnostics while cached analysis k…

NameTypeReqDescription
allow_remote_extendsboolean|null–Allow trusted HTTPS config `extends` for this request. Defaults to false and never grants process-global trust.
changed_sincestring|null–Git ref to compare against when limiting candidates to changed files.
changed_workspacesstring|null–Scope candidates to workspaces touched since this git ref. Mutually exclusive with `workspace`.
configstring|null–Path to a fallow config file.
gatestring|null–Optional security regression gate. Valid values: "new" or "newly-reachable". The "newly-reachable" gate requires `changed_since`.
max_output_bytesinteger|null–Byte cap for this call's response. Lowers the server cap (default 1000000); over it the call is REFUSED (`isError`, `exit_code: 2`).
no_cacheboolean|null–Disable the incremental parse cache.
pathsarray|null–Scope candidates to just-edited files for the agent edit loop. Each path is passed to `fallow security --file` and matches finding anchors or trace hops.
rootstring|null–Project root; defaults to the working directory.
surfaceboolean|null–Include the attack-surface inventory with defensive-boundary verification prompts in the JSON response.
threadsinteger|null–Parser thread count; defaults to CPU cores.
workspacestring|null–Workspace packages to scope candidates to; mutually exclusive with `changed_workspaces`.

No output schema declared.

No examples provided.

symbol_impact ~272

Return exact-symbol consumers, transitive affected files, and targeted tests for a TypeScript export or exported class method. Select either export_name, or both class_name and member_name. The result is advisory project-impact evidence and does not duplicate tsc or Oxlint diagnostics.

NameTypeReqDescription
allow_remote_extendsboolean|null–Allow trusted HTTPS config `extends` for this request. Defaults to false and never grants process-global trust.
class_namestring|null–Exact exported class name. Must be paired with `member_name`.
configstring|null–Path to a fallow config file.
export_namestring|null–Exact exported symbol name. Mutually exclusive with the class-method selector.
filestringyesProject-root-relative declaration file.
member_namestring|null–Exact method name. Must be paired with `class_name`.
no_cacheboolean|null–Disable the incremental parse cache.
rootstring|null–Project root; defaults to the working directory.
threadsinteger|null–Parser thread count; defaults to CPU cores.
type_aware_projectsarray|null–Explicit tsconfig paths. Project auto-discovery is used when omitted.
type_aware_require––Whether incomplete semantic evidence is advisory or gating.

No output schema declared.

No examples provided.

trace_clone ~733

Deep-dive a duplicate-code clone group. Address it either by a source location (file + line) or by a stable fingerprint (fingerprint="dup:<id>" from a find_dupes clone_groups[].fingerprint, usually dup:<8hex> and widened only on rare report collisions). Returns the matched clone instance, every sibling clone group / location, plus per group an extract-function suggestion with estimated line savings and a best-effort suggested_name (the field is omitted, not null, when there is no confident name, so branch on key presence; advisory, verify before applying, never auto-apply). Provide exactly one addressing form. Import declarations are excluded from clone detection by default; pass ignore_imports=false to count them again. Use after find_dupes when consolidating duplication and you need exact sibling locations and a refactor target.

NameTypeReqDescription
allow_remote_extendsboolean|null–Allow trusted HTTPS config `extends` for this request. Defaults to false and never grants process-global trust.
configstring|null–Path to a fallow config file.
cross_languageboolean|null–Enable cross-language detection (strips TypeScript type annotations for TS/JS matching).
filestring|null–Project-relative path to a file containing the clone instance. Used with `line` to address by source location; omit when using `fingerprint`.
fingerprintstring|null–Stable clone-group identity (`dup:<id>`) from a `find_dupes` `clone_groups[].fingerprint`. Alternative to addressing by `file` plus `line`.
ignore_importsboolean|null–Exclude import declarations from clone detection. Defaults to `true` (sorted import blocks are a formatting artifact, not copy-paste); set `false` to count them again.
ignore_symlinksboolean|null–Omit clone instances whose path is a symlink or lies under a symlinked directory. Defaults to the project config; set `false` to report them even when the config sets `ignoreSymlinks`.
lineinteger|null–Line number of the clone instance within `file`. Used with `file` to address by source location; omit when using `fingerprint`.
min_linesinteger|null–Minimum line count for a clone. Defaults to the project config, or 5 if unset.
min_occurrencesinteger|null–Minimum number of occurrences before a clone group is reported. Defaults to the project config, or 2 if unset.
min_tokensinteger|null–Minimum token count for a clone. Defaults to the project config, or 50 if unset.
modestring|null–Detection mode: "strict", "mild", "weak", or "semantic". Defaults to the project config, or "mild" if unset.
nearboolean|null–Detect function-scoped near-miss clones before resolving the trace.
no_cacheboolean|null–Disable the incremental parse cache.
rootstring|null–Project root; defaults to the working directory.
skip_localboolean|null–Only report cross-directory duplicates.
threadsinteger|null–Parser thread count; defaults to CPU cores.
thresholdnumber|null–Fail if duplication exceeds this percentage (0 = no limit). Defaults to the project config, or 0 if unset.
workspacestring|null–Workspace packages to analyze: name or repo-relative path, comma-separated list, globs, `!` negation.

No output schema declared.

No examples provided.

trace_dependency ~478

Trace where a dependency is used. Returns which files import the package, which imports are type-only, whether the package is referenced from package.json scripts or CI configs (`used_in_scripts`), and whether the dependency is used at all (`is_used` accounts for imports, script usage, and the used packages that list it as a peer (`peer_of`), matching the unused-deps detector). `unused_in` names each manifest that the detector still flags, because an import credits only the nearest manifest that installs the package. Set `usage`, `specifiers`, `sites` (paged with `limit` and `cursor`) or `closure_depth` to add a `usage` object: per imported name, the file, call and unresolved counts, one hop through project wrappers, and the usage sites. Useful before removing a dependency, moving it between dependencies and devDependencies, or migrating its API.

NameTypeReqDescription
allow_remote_extendsboolean|null–Allow trusted HTTPS config `extends` for this request. Defaults to false and never grants process-global trust.
closure_depthinteger|null–Add importers of the users, up to this depth. Implies `usage`.
configstring|null–Path to a fallow config file.
cursorstring|null–`usage.sites.next_cursor` of the previous page.
limitinteger|null–Sites per page (default 50). Implies `sites`.
no_cacheboolean|null–Disable the incremental parse cache.
package_namestringyesName of the npm package to trace usage for.
productionboolean|null–Production mode: exclude test, story, and dev files, only start/build scripts, and report type-only dependencies.
rootstring|null–Project root; defaults to the working directory.
sitesboolean|null–Add one page of usage sites. Implies `usage`.
specifiersarray|null–Imported names to report. Implies `sites`.
threadsinteger|null–Parser thread count; defaults to CPU cores.
usageboolean|null–Add the per-name `usage` counts.
workspacestring|null–Workspace packages to analyze: name or repo-relative path, comma-separated list, globs, `!` negation.

No output schema declared.

No examples provided.

trace_error ~544

Resolve a runtime stack trace against the project graph: paste the trace text in `trace` and get, per frame, which definitions in THIS project the frame's identifier names. The verb for "my service threw this in production, what code is that". Returns `kind: "trace-error"` with retained frames in input order, each carrying an `origin` (`in_project`, `node_modules`, `out_of_corpus`) and a `resolution` (`resolved`, `ambiguous`, `not_found`, `not_attempted`), plus `candidates[]` naming the file, symbol, member and declaration line. It is built to refuse overclaiming: a frame matching several definitions is `ambiguous`, with bounded candidates and `candidates_omitted` instead of a preferred match, a frame the graph was never asked about is `not_attempted` rather than a softer `not_found`, and `line_mismatch` marks a resolved frame whose own line sits at a different declaration, so a name-only match is visible instead of implied. `counts` closes over the reported frames and publishes `frames_omitted` and `unparsed_lines`, so a capped or unreadable input cannot look complete. No source maps are read: a frame inside built output says so instead of being rebound through a map that may be stale, so give it a trace from unbundled source or the source paths a map already resolved. The RESOLUTION outcome never fails the call: a trace in which nothing resolves is an ANSWER, and exits 0. A refused input still is a refusal: an empty or oversized `trace` returns `isError` with `FALLOW_INVALID_TRACE_OPTIONS`.

NameTypeReqDescription
allow_remote_extendsboolean|null–Allow trusted HTTPS config `extends` for this request. Defaults to false and never grants process-global trust.
configstring|null–Path to a fallow config file.
no_cacheboolean|null–Disable the incremental parse cache.
productionboolean|null–Production mode: exclude test, story, and dev files, only start/build scripts, and report type-only dependencies.
rootstring|null–Project root; defaults to the working directory.
sourcestring|null–Where the trace came from, echoed back as the payload's `source`.
threadsinteger|null–Parser thread count; defaults to CPU cores.
tracestringyesThe runtime stack trace text, pasted verbatim.
workspacestring|null–Workspace packages to analyze: name or repo-relative path, comma-separated list, globs, `!` negation.

No output schema declared.

No examples provided.

trace_export ~400

Trace why an export is considered used or unused. Returns file reachability, entry-point status, direct references, re-export chains, the framework plugin rules that mark the export as used (`plugin_credits`), and a concise reason string. If export_name is a class / enum / store MEMBER rather than a top-level export, returns a member trace instead (carrying member_name, member_kind, owner_export, owner_is_used) that reports the owning class's reachability and usage plus a pointer to the matching --unused-<kind>-members command, so a class-member finding can be debugged too. Use this when an agent needs evidence before deleting or rewriting a supposedly unused export or class member. References carry `search_visibility`; see fallow://tools/trace_export. When the config or FALLOW_TYPE_AWARE turns type-aware analysis on, the trace also carries a `semantic` block with checker-backed evidence, as `fallow dead-code --trace` does.

NameTypeReqDescription
allow_remote_extendsboolean|null–Allow trusted HTTPS config `extends` for this request. Defaults to false and never grants process-global trust.
configstring|null–Path to a fallow config file.
export_namestringyesName of the exported symbol (or class/enum/store member) to trace.
filestringyesProject-relative path to the file that declares the export.
no_cacheboolean|null–Disable the incremental parse cache.
productionboolean|null–Production mode: exclude test, story, and dev files, only start/build scripts, and report type-only dependencies.
rootstring|null–Project root; defaults to the working directory.
threadsinteger|null–Parser thread count; defaults to CPU cores.
workspacestring|null–Workspace packages to analyze: name or repo-relative path, comma-separated list, globs, `!` negation.

No output schema declared.

No examples provided.

trace_file ~236

Trace a file's graph context. Returns whether the file is reachable or an entry point, what it exports, what it imports, what imports it, and which re-exports it declares. Use this to understand whether a file is isolated, barrel-only, or imported by live entry points.

NameTypeReqDescription
allow_remote_extendsboolean|null–Allow trusted HTTPS config `extends` for this request. Defaults to false and never grants process-global trust.
configstring|null–Path to a fallow config file.
filestringyesProject-relative path to the file to trace.
no_cacheboolean|null–Disable the incremental parse cache.
productionboolean|null–Production mode: exclude test, story, and dev files, only start/build scripts, and report type-only dependencies.
rootstring|null–Project root; defaults to the working directory.
threadsinteger|null–Parser thread count; defaults to CPU cores.
workspacestring|null–Workspace packages to analyze: name or repo-relative path, comma-separated list, globs, `!` negation.

No output schema declared.

No examples provided.

trace_import_path ~284

Shortest import path from one module to another, hop by hop with each hop's import line and whether the hop is type-only. Unreachable answers `reachable: false`; the same module answers `reachable: true`. Both report `hops: 0`, so branch on `reachable`, not the count. Exact project paths take priority; ambiguous abbreviations are refused. Use trace_file for one file's direct neighbours.

NameTypeReqDescription
allow_remote_extendsboolean|null–Allow trusted HTTPS config `extends` for this request. Defaults to false and never grants process-global trust.
configstring|null–Path to a fallow config file.
fromstringyesProject-relative path of the module the walk starts from.
no_cacheboolean|null–Disable the incremental parse cache.
productionboolean|null–Production mode: exclude test, story, and dev files, only start/build scripts, and report type-only dependencies.
rootstring|null–Project root; defaults to the working directory.
threadsinteger|null–Parser thread count; defaults to CPU cores.
tostringyesProject-relative path of the module the walk is looking for.
workspacestring|null–Workspace packages to analyze: name or repo-relative path, comma-separated list, globs, `!` negation.

No output schema declared.

No examples provided.

trace_symbol ~322

Trace an exact TypeScript symbol with checker-backed references, namespace identity, aliases, and re-export hops. Root trace fields preserve syntactic context; treat `semantic.references`, `semantic.status`, and `semantic.identity` as the authoritative exact evidence. The proof covers only the lane named by `semantic.target.namespace`, so a root trace that lists a reference the proof does not is wider evidence rather than stale. This is project-wide evidence for Fallow decisions, not a compiler-diagnostic or lint-rule surface.

NameTypeReqDescription
allow_remote_extendsboolean|null–Allow trusted HTTPS config `extends` for this request. Defaults to false and never grants process-global trust.
configstring|null–Path to a fallow config file.
export_namestringyesName of the exported symbol to trace.
filestringyesProject-relative path to the file that declares the export.
max_output_bytesinteger|null–Byte cap for this call's response. Lowers the server cap (default 1000000); over it the call is REFUSED (`isError`, `exit_code: 2`).
no_cacheboolean|null–Disable the incremental parse cache.
rootstring|null–Project root; defaults to the working directory.
threadsinteger|null–Parser thread count; defaults to CPU cores.
type_aware_projectsarray|null–Explicit tsconfig paths. Project auto-discovery is used when omitted.
type_aware_require––Whether incomplete semantic evidence is advisory or gating.

No output schema declared.

No examples provided.

Install

How do I install the Fallow MCP server?

Fallow runs locally as an npm package, launched with npx -y fallow mcp-server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · fallow

# add to Claude Code
claude mcp add fallow-rs-fallow -- npx -y fallow mcp-server
Common questions

What is the Fallow MCP server?

Fallow is an MCP server listed in the public MCP registry as io.github.fallow-rs/fallow. Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools. This page covers its npm package (fallow).

Is the Fallow MCP server safe to use?

Fallow scores 83 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Fallow MCP server expose?

Fallow exposes 44 tools: analyze, audit, check_architecture, check_changed, check_health, and 39 more. Their descriptions and schemas cost roughly 30,711 tokens of context every time the server is loaded.

Is the Fallow MCP server still maintained?

Fallow is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the Fallow MCP server under?

Fallow declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the Fallow MCP server?

VerifyMCP ran 16 checks on Fallow, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.