MCP server for 0Latency — persistent memory layer for AI agents. Give Claude, Cursor, or any MCP client long-term memory.
Free
Nothing to run from here
Th0th Ai Client 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.
Open Installation—
p95 latency
—
call success
local
runs on your machine
—
calls last 7d
What it does
th0th MCP server - Semantic code search, memory, and context compression via Model Context Protocol
Quickstart
# 1 — run it from where its publisher ships it
npx -y @th0th-ai/mcp-client
# 2 — the plan is chosen at checkout, in the browser
# 3 — ask your agent something
> th0th MCP server - Semantic code search, memory, and context compression via Model Context Protocol
Publishernot claimed
THAll 1 server
@th0th-ai1 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 Th0th Ai Client 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. It is scanned, signed and pinned to the version you choose — 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. Claude Code registers it in one command.
claude mcp add th0th-ai-client-mcp -- npx -y @th0th-ai/mcp-clientReconnect, or start a new session, and the tools appear in the model’s tool list.
This is a paid listing, so the CLI has to be signed in and the licence has to be on your account — how the login works. Until then the install stops with the price rather than half-writing a config entry.
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
20 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.
Index a project directory for contextual code search with semantic embeddings
Takes no parameters.
Example callreturns →
Get the status of a background indexing job by its jobId. Use this after calling th0th_index to check progress.
Takes no parameters.
Example callreturns →
Search for code in an indexed project using semantic and keyword search
Takes no parameters.
Example callreturns →
Store memory in the hierarchical memory system (local SQLite)
Takes no parameters.
Example callreturns →
Search stored memories across sessions using semantic search (recovers context from previous conversations)
Takes no parameters.
Example callreturns →
Compress context using semantic compression (keeps structure, removes details)
Takes no parameters.
Example callreturns →
Retrieve and compress context with maximum token efficiency (search + compress)
Takes no parameters.
Example callreturns →
Get search analytics and performance metrics (usage patterns, cache performance, etc)
Takes no parameters.
Example callreturns →
List all indexed projects with their status (pending/indexing/indexed/error), file counts, symbol counts, and last indexed time.
Takes no parameters.
Example callreturns →
Search for symbol definitions (functions, classes, variables, types, interfaces) in an indexed project. Returns name, kind, file location, line numbers, and doc comments.
Takes no parameters.
Example callreturns →
Find all references (usages) of a symbol across the project. Returns file paths, line numbers, reference kinds (call/import/type_ref/extend/implement), and code context snippets.
Takes no parameters.
Example callreturns →
Find the definition of a symbol (function, class, variable, type, etc.) in the project. Disambiguates by calling file context. Returns file location, line numbers, doc comment, and code snippet.
Takes no parameters.
Example callreturns →
Delete all indexed data for a project: vector embeddings, symbol graph (definitions/references/imports/centrality), and stored memories.
Takes no parameters.
Example callreturns →
Read a specific file (or line range) with symbol metadata and imports. Use instead of Read/grep when you have filePath+lineStart+lineEnd from a search result.
Takes no parameters.
Example callreturns →
Create/resume a Synapse cognitive session. Returns sessionId to pass as sessionId on every th0th_search. Activates task alignment, agent affinity, working-memory buffer. Name by intent:
Takes no parameters.
Example callreturns →
Seed the Synapse working-memory buffer with recalled memories before searching. Call at session start with th0th_recall results.
Takes no parameters.
Example callreturns →
Record file access for affinity scoring — boosts that file in future searches. Call after reading or editing a file.
Takes no parameters.
Example callreturns →
Get raw code snippet by file + line range from an indexed project.
Takes no parameters.
Example callreturns →
Browse stored memories by type/importance without a semantic query (audit mode). Use th0th_recall for semantic search.
Takes no parameters.
Example callreturns →
Force full reindex of a project workspace. Use when autoReindex (max 50 files) is insufficient after a large refactor.
Takes no parameters.
Example callreturns →
Startermost installed
$14 / month
- 11,000 calls a month, included
- 132 calls a minute at peak
- Every tool the listing has
- Cancel any time — the unused days are credited
- Runs behind the gateway, so cancelling stops it
Pro
$44 / month
- 60,000 calls a month, included
- 720 calls a minute at peak
- Every tool the listing has
- Cancel any time — the unused days are credited
- Runs behind the gateway, so cancelling stops it
Scale
$94 / month
- 280,000 calls a month, included
- 3,360 calls a minute at peak
- Every tool the listing has
- Cancel any time — the unused days are credited
- Runs behind the gateway, so cancelling stops it
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
No call is billed on its own, and this plan carries no monthly call limit. $14 a month covers every tool 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: $8.42
$16.58 left
ATrust score 93 / 100
Release 2.0.2 · scanned 25 Aug 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 score93
Findings0 threat · 1 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digest92d07ef099d0542957924152a6bc5dc13b2cc271a900aa098515250943cac1e4
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| 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 surfacenot available
Implementation sourceread
Package metadataread
Live transportnot available
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, 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 |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
can execute shell commands or code
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 digest92d07ef099d05429
Scanned2026-08-25
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
Pinned to 2.0.2 — the install command below asks for that release. A pin is part of an install, so it is kept for this visit and written down when you install.
2.0.2
undated
installedNo release note was published with this version.
—
no reviews yet
Reviews are earned
Only accounts with at least 50 real tool calls against this server in the last 90 days can post. Ratings are weighted by how much the reviewer actually uses it, and publishers can reply once per review.
Reviews are earned
Writing one takes an account with at least 50 real tool calls against Th0th Ai Client in the last 90 days. That is the whole gate — there is no other way to post, which is why the counts beside each review are worth reading.
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 an account with 50 real tool calls against it.