Query Markup Documents - On-device hybrid search for markdown files with BM25, vector search, and LLM reranking
Nothing to run from here
Saihm Pro 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.
97/100
trust score
30
downloads a day
local
runs on your machine
3k
downloads in 30d
What it does
Unlock persistent, sovereign memory for your AI agents across models and platforms with SAIHM. Featuring zero-knowledge encryption, 85% token savings, and provable cryptographic right-to-erasure. Capabilities: https://www.youtube.com/watch?v=t3rXudDKank
Quickstart
Run once first — the server needs this before it answers:
npx -y @saihm/mcp-server-pro free-join# 1 — add it to Claude Code
claude mcp add --scope user saihm-pro-mcp '--' npx -y @saihm/mcp-server-pro
# 2 — ask your agent for something these tools do
# saihm_remember, saihm_recall, saihm_forget and 6 more
Saihm Pro costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for. Saihm Pro itself has its own plans, which mcprush does not sell or bill.
PublisherVerified · since 2026
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 Saihm Pro 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 Node.js — the current LTS (24) is the safe choice; npx comes with it. Run once first: npx -y @saihm/mcp-server-pro free-join. 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 saihm-pro-mcp '--' npx -y @saihm/mcp-server-proReconnect, 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 asks of you
Nothing is required, but it can take SAIHM_ENDPOINT_URL (SAIHM operator endpoint. Optional: defaults to the hosted service at https://saihm.coti.global/mcp.), SAIHM_SELF_JOIN (Self-join is ON by default: the saihm_join tool generates a non-custodial identity on this device and activates the free trial, so no master secret is needed. S), SAIHM_MASTER_SECRET_FILE (Path to a mode-600 file holding a 64+ hex-char master secret. Only needed if you opt out of self-join or are restoring an existing identity. Never transmitted.), SAIHM_HOME (Base dir for the self-join identity file ($SAIHM_HOME/free-identity.key, mode 600). Defaults to ~/.saihm. Also the fallback state directory when SAIHM_STATE_DIR) if you want to set them.
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
9 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.
Store information in SAIHM persistent memory. Encryption happens in this process and the key never leaves it, so the server holds ciphertext it cannot read. Use this when a fact, decision, or piece of context should outlive the current session. Pass an existing cellId to update that cell instead…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| content | string | no | Information to remember. Required unless warmStart is "put". |
| cellId | yes | — | |
| warmStart | yes | — | |
| coversThrough | yes | — | |
| token | yes | — |
Retrieve your memories from SAIHM and decrypt them in this process; the server never sees plaintext. Use this at the start of a session, or whenever past context is needed. Pass query to filter by keyword, or leave it out to load everything. Pass cellId alone to read one of your own cells. To read…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | yes | — | |
| sharerPinnedAgentIdHashHex | yes | — | |
| sharerRecord | yes | — | |
| cellId | yes | — | |
| shareEntries | yes | — | |
| listOnly | yes | — | |
| sharesOnly | yes | — | |
| after | yes | — | |
| warmStart | yes | — | |
| token | yes | — |
Cryptographically erase one memory by its cell id (GDPR Art. 17). Destroying the wrapped key leaves the content unreadable to everyone, the operator included. Irreversible: use it when erasure is the intent, not to tidy a working set. With warmStart "delete", it instead destroys one encrypted…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | no | Memory cell id (hex) to erase. Required unless warmStart is "delete". |
| warmStart | yes | — | |
| snapshotId | yes | — | |
| token | yes | — |
Show the current SAIHM session: the agent identity, which this client derives locally, plus the tier, custody mode, shard and sharing counts, and bfsi score the server reports. No plaintext appears, because the server holds none. Use it to check which identity is active and what is stored and…
No parameter schema on file.
Grant one other agent access to a single memory cell, named by cellId. Identify the recipient by their recipientPinnedAgentIdHashHex, pinned out-of-band, and their recipientRecord. Set scope to 'read', 'write' or 'readwrite'. Only that one cell is exposed, and sharing re-wraps its key rather than…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| cellId | string | yes | The cell to share |
| recipientRecord | object | yes | The grantee's published identity record (hex fields) |
| recipientPinnedAgentIdHashHex | string | yes | The grantee's agentIdHash (hex), pinned out-of-band |
| scope | yes | — | |
| expiryEpoch | yes | — |
Withdraw a grant made with saihm_share, naming the same cellId and the recipient's recipientHex. It applies to future reads and cannot retract what the recipient has already read. Use it to end access; the memory itself remains, and saihm_forget is what erases.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| cellId | string | yes | The shared cell id |
| recipientHex | string | yes | The grantee's agentIdHash (hex) to revoke |
Open a protocol governance proposal: set scope to 'emission_param' or 'protocol_upgrade', and for 'emission_param' also pass paramKey and proposedValue. Protocol governance is not enabled for this client yet — the tool is present so the surface stays stable, and calling it returns a 'governance…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| scope | string | yes | Governable scope |
| paramKey | yes | — | |
| proposedValue | yes | — |
Cast a vote on an open protocol governance proposal by its proposalId, with approve set to true to approve or false to reject. Protocol governance is not enabled for this client yet — the tool is present so the surface stays stable, and calling it returns a 'governance unavailable' error rather…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| proposalId | string | yes | Hex proposalId |
| approve | boolean | yes | true = approve, false = reject |
Activate free SAIHM persistent memory for this agent. Call this when the user asks to join, sign up for, or set up SAIHM. Where no identity is configured, a join creates a NEW, EMPTY memory: first ask whether they already have a SAIHM identity (from another machine or an earlier session) - if so,…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| newIdentity | yes | — |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under Apache-2.0
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
- Saihm Pro itself has its own plans, which mcprush does not sell or bill
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Saihm Pro 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 97 / 100
Release 0.14.1 · scanned 15 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 score97
Findings0 threat · 1 capability
Capabilitymoderate
Coveragesource
Verificationsource
Surface digest16f814cecec05d1fbf206c4888eedfdae830bcec323003da327f099f99943b5d
Score vectorthreat 100 → client 97
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| 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 (9 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>".
1 of the 9 recovered tools are registered only when selfJoinEnabled() holds (dist/server.js:1058) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 8.
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. moderate is the level these add up to.
8 tools are registered unconditionally · 1 more only when selfJoinEnabled() holds (dist/server.js:1058) — typically when a key or option is configured. All 9 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| saihm_remember | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| saihm_recall | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| saihm_forget | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| saihm_status | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| saihm_share | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| saihm_revoke_share | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| saihm_governance_propose | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| saihm_governance_vote | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| saihm_join conditional | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
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.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest16f814cecec05d1f
Scanned2026-10-15
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 0.14.1. Pin a release below and the command asks for exactly that one.
0.14.1
13 Oct 2026
latestNo release note was published with this version.
0.14.0
10 Oct 2026
No release note was published with this version.
0.13.0
5 Oct 2026
No release note was published with this version.
0.12.1
4 Oct 2026
No release note was published with this version.
0.12.0
2 Oct 2026
No release note was published with this version.
0.11.2
23 Sep 2026
No release note was published with this version.
0.11.0
17 Sep 2026
No release note was published with this version.
0.10.0
14 Sep 2026
No release note was published with this version.
0.7.0
13 Sep 2026
No release note was published with this version.
0.5.3
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
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 Saihm Pro 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.