Pack local or remote codebases into AI-friendly files that LLMs and coding agents can read or search
Nothing to run from here
Semantic Cache is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
94/100
trust score
14
tools declared
local
runs on your machine
—
downloads a day
What it does
File cache for coding agents: re-reads cost ~40 tokens, changed files return diffs.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user semantic-cache-mcp '--' uvx semantic-cache-mcp
# 2 — ask your agent for something these tools do
# read, read_image, stats and 11 more
Semantic Cache costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
COAll 1 server
CoderDayton1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Semantic Cache as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user semantic-cache-mcp '--' uvx semantic-cache-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
14 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Read a file, returning as few tokens as possible. For 2+ files, use batch_read.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | File path (absolute, or relative to the project root). Use an absolute path for files outside the project root. |
| max_size | integer | no | Byte threshold above which a map of the file is returned instead of its text; read exact lines with offset/limit. |
| offset | integer | no | 1-based first line for a ranged read; omit or pass 0 to start from the first line. |
| limit | integer | no | Number of lines to return starting at offset. |
| known_hash | string | no | The content_hash from your last read of this file — or the coverage_token from your last ranged read of it — passed back to get "unchanged" instead of the content re-sent. Omit only on a first r |
| outline | boolean | no | Return the file's definitions and their line numbers instead of its text. Cannot be combined with offset/limit. |
| line_numbers | boolean | no | Prefix each line of a ranged read with its number. Costs about 17% more tokens; the range is in lines either way. Requires offset or limit. |
Read an image file so the model can see it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | Image file path (absolute, or relative to the project root). |
Report cache health, token savings, and runtime diagnostics.
Takes no parameters.
Empty the cache. Does not touch any project file.
Takes no parameters.
Delete one file or symlink and evict its cache entries.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | File or symlink path (absolute, or relative to the project root). |
| dry_run | boolean | no | Preview the outcome without deleting or evicting the cache. |
Create a file or replace its entire contents.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | File path to create or replace (absolute, or relative to root). |
| content | string | yes | Full file content, or the text to append when append=true. |
| create_parents | boolean | no | Create any missing parent directories. |
| dry_run | boolean | no | Preview the result without writing. |
| auto_format | boolean | no | Run the formatter after writing. |
| show_diff | boolean | no | Return the unified diff even on a deterministic write. |
| append | boolean | no | Append content to the end of the file instead of overwriting. |
| known_hash | string | no | The content_hash you hold for this file. Only needed for append, to prove you hold the part you are not resending. |
Edit one file by exact text replacement.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | File path to modify (absolute, or relative to root). |
| old_string | string | no | Exact text to find. Omit only for a line-range replacement. |
| new_string | string | no | Replacement text (an empty string deletes the match). |
| replace_all | boolean | no | Replace every occurrence instead of requiring a unique match. |
| dry_run | boolean | no | Preview without writing. |
| auto_format | boolean | no | Run the formatter after editing. |
| show_diff | boolean | no | Return the diff even on a deterministic edit. |
| start_line | integer | no | 1-based inclusive start line for a scoped or line-range edit. |
| end_line | integer | no | 1-based inclusive end line for a scoped or line-range edit. |
| known_hash | string | no | The content_hash from your last read of this file. Proves you hold the text being edited, so the result can be handed back as a claimable content_hash. |
Show where old_string would match in a file, without editing it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | File path to search (absolute, or relative to root). |
| old_string | string | yes | Anchor text to locate. Must match exactly, including whitespace and indentation. Cannot be empty. |
Apply many exact edits to one file in a single atomic call.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | File path to modify (absolute, or relative to root). |
| edits | string | yes | JSON array of edit entries, in any of the forms above. |
| dry_run | boolean | no | Preview without writing. |
| auto_format | boolean | no | Run the formatter after all edits. |
| show_diff | boolean | no | Return the full diff even on a deterministic all-success batch. |
| known_hash | string | no | The content_hash from your last read of this file. Proves you hold the text being edited, so the result can be handed back as a claimable content_hash. |
Find cached files by keyword relevance (BM25 ranking).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Keywords to rank by. Natural-language phrasing is fine, but ranking is on the individual words. |
| k | integer | no | Maximum number of matches to return. |
| directory | string | no | Restrict matches to files under this directory. Defaults to the project root. |
| show_preview | boolean | no | Include a short preview line for each match. |
Read several files at once under a shared token budget.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| paths | string | yes | The files to read — a comma-separated list, a JSON array, or glob patterns (expanded for you). |
| max_total_tokens | integer | no | Total token budget shared across the whole batch. |
| priority | string | no | Optional paths to read first, ahead of the remaining files. Ordering only — a priority file still has to fit the budget, and is skipped like any other when it does not. |
| known_hashes | string | no | JSON object mapping a path to the content_hash you still hold for it, e.g. {"src/a.py": "8f3c..."}. Any file you cannot vouch for this way is sent in full. |
Index files into the cache so grep and search can see them, returning counts only.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| paths | string | yes | Files to index — a comma-separated list, a JSON array, or glob patterns (expanded for you, e.g. src/**/*.py). |
| max_files | integer | no | Cap on files indexed in this call. Matches beyond it are left out and flagged with truncated. |
List files matching a glob and show which are already cached.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pattern | string | yes | Glob pattern to match (e.g. src/**/*.py). |
| directory | string | no | Base directory the pattern is evaluated from. |
| cached_only | boolean | no | Return only files that are already cached. |
Search cached file contents for an exact string or regex.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pattern | string | yes | A regular expression, or a literal string when fixed_string=true. |
| path | string | no | Optional filter — an exact path, a path suffix, a directory (matching every cached file beneath it), or a glob. |
| fixed_string | boolean | no | Match pattern literally instead of as a regex. |
| case_sensitive | boolean | no | Match case-sensitively. |
| context_lines | integer | no | Lines of surrounding context to include around each match. Overlapping windows are merged, so no line is sent twice. |
| max_matches | integer | no | Cap on total matches returned across all files. |
| max_files | integer | no | Cap on the number of files returned. |
| output | string | no | How much to return — matches (default), paths for the matching files without their lines, or count for the totals alone. |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Semantic Cache or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 94 / 100
Release 0.7.0 · scanned 28 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score94
Findings5 threat · 1 capability
Capabilityhigh
Coveragesource
Verificationsource
Surface digest7335cc2cef73b8675299add8d41f2422e8909fbcd5e8352cb908ded144804e6c
Score vectorthreat 100 → client 94
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (14 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| read | no tags | |
| read_image | no tags | |
| stats | no tags | |
| clear | no tags | |
| delete | no tags | |
| write | no tags | |
| edit | no tags | |
| edit_preview | no tags | |
| batch_edit | no tags | |
| search | no tags | |
| batch_read | no tags | |
| warm | no tags | |
| glob | sensitive-source | sensitive-source: keyword "list_files" |
| grep | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest7335cc2cef73b867
Scanned2026-10-28
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.7.0. Pin a release below and the command asks for exactly that one.
0.7.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Semantic Cache can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.