Hatun MCP - Governed Agent Gateway
Governed MCP gateway: policy gate on every tool call, hash-chained DSSE receipt on every result.
Connector by szl-holdings · GitHub account verified by the MCP Registry
Chalk Labs
Need help deploying Hatun MCP - Governed Agent Gateway?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.
npx agentmarket install connector/szl-holdings-hatun-mcp
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 26, 2026.
- Tools
- 18 read · 2 write · 0 delete · 6 not yet classified
- Secrets
- 1 (API keys, tokens or passwords)
- Install scripts
- None found
- Runs as
- Docker image
Tools by what they do 26
Read from the source code; the running server may list different tools.
Read 18 · Look things up without changing anything.
governance_pacbayes_boundmesh_quorum_statusszl_a11oy_code_chatszl_a11oy_operator_reasonszl_a11oy_sentinel_scanszl_anatomy_3d_renderszl_companion_reasonszl_doctrine_lookupszl_drone_lookupszl_formula_evaluateszl_github_estate_snapshotszl_immune_scan
Show 6 more tools
szl_khipu_verifyszl_killinchu_detectszl_lean_verifyszl_puriq_evaluateszl_thesis_queryszl_yuyay_score
Write 2 · Create, change, send or run things.
dsse_signkhipu_append_and_verify
Not yet classified 6 · We could not tell from the name and description.
puriq_master_toolszl_killinchu_cueszl_lambda_quorumszl_wayra_recentszl_yachay_dome_predictyuyay_gate_check
Secrets and settings it asks for
Secrets: values you paste in that let it act as you.
HATUN_MCP_SIGNING_KEY
Other settings (environment variables or headers).
HATUN_MCP_DISABLE_DYNAMIC
Network hosts it talks to 14
a-11-oy.com· found in codea11oy.net· found in codeapi.github.com· found in codegithub.com· found in codehuggingface.co· found in codein-toto.io· found in coderouter.huggingface.co· found in codesmithery.ai· found in codeszlholdings-anatomy-3d.hf.space· found in codeszlholdings-hatun-mcp.hf.space· found in codeszlholdings-killinchu.hf.space· found in codeszlholdings-lean-kernel.hf.space· found in codeszlholdings-szl-second-brain.hf.space· found in codeszlholdings.com· found in code
Files it touches
- Any path the agent passes to its tools
Tools (26)
Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].
dsse_signSign `payload` with a real ECDSA P-256 DSSE envelope. Uses the server's live signer (loaded from HATUN_MCP_SIGNING_KEY). When no key is present in this process, returns honesty='UNSIGNED' with an empty signatures[] (disclosed, never faked). key_env_var documents which env var the Cosign Bootstrap squad will populate (SZL_COSIGN_PRIVATE_PEM).
governance_pacbayes_boundCompute the published PAC-Bayes governance-ensemble bound (F7). REAL closed-form; inputs caller-supplied. Emits a Khipu receipt.
khipu_append_and_verifyAppend one Khipu link carrying `payload` and recompute-verify the chain. parent_hash is advisory (the live chain links to its own last hash); when supplied and it does not match the live tip, we disclose the mismatch.
mesh_quorum_statusByzantine n>=3f+1 mesh-quorum status over the named organs. Returns n, f, threshold (=2f+1), the input presence set, and the arithmetic quorum boolean. `present` is caller-declared data, not a live cluster probe; live_polled and operational_quorum therefore fail closed. Traces to lutar-lean KhipuConsensus.lean::khipu_consensus_safety.
puriq_master_toolTHE named PURIQ entrypoint over MCP. PURIQ(input, context) -> (Lambda in [0,1], DSSE-signed Khipu receipt, traceparent chain, 13-axis breakdown). Composes Yuyay-13 -> quorum -> HUKLLA -> Khipu append -> DSSE-sign using the server's LIVE chain + signer.
szl_a11oy_code_chatChat with a11oy.code — the unified open-LLM router (7-tier, GREEN-first). Calls a11oy POST /v1/router. messages = OpenAI-style [{role, content}, ...].
szl_a11oy_operator_reasona11oy Operator reasoning — a11oy-named twin of szl_companion_reason. Reason over a question + context. Calls the live a11oy companion organ POST /api/a11oy/v1/companion/ask.
szl_a11oy_sentinel_scana11oy Sentinel inline immune screen — a11oy-named twin of szl_immune_scan. Screen code, an SBOM, or a container image for threat signatures. Calls the live a11oy immune organ POST /api/a11oy/v1/immune/verdict.
szl_anatomy_3d_renderReturn a URL to a Three.js scene snapshot of an organ in the SZL 3D anatomy.
szl_companion_reasonAsk the a11oy companion to reason over a question + context. Calls the live a11oy companion organ POST /api/a11oy/v1/companion/ask (answers only from live platform data; refuses to fabricate). (Renamed 2026-06-16 from the retired codename tool; see DEPRECATED.md.)
szl_doctrine_lookupSemantic lookup across SZL Doctrine v11/v12/v13 + thesis v20. Routed via the a11oy companion grounded-RAG over the doctrine corpus.
szl_drone_lookupReturn the canonical drone DB entry from the killinchu drone database. Calls killinchu GET /v1/drones.
szl_formula_evaluateEvaluate a named doctrine formula primitive (real closed-form arithmetic). Known: 'puriq' (master operator P(x,t)), 'kl_divergence', 'sigmoid', 'liu_hui_pi'. Unknown names are forwarded to the live lutar-lean kernel /formula-eval route.
szl_github_estate_snapshotObserve the fixed public szl-holdings GitHub estate with bounded GETs. Returns structural repository and open-PR/check evidence plus a canonical SHA-256 digest. It never accepts a URL, organization, token, cursor or mutation. Private repositories, default-branch head SHAs, deployments, model training and runtime health are explicitly outside this v1 scope. Missing pages, rate limits or malformed evidence produce INCOMPLETE or UNAVAILABLE. Signing availability is reported separately by the envelope.
szl_immune_scana11oy Immune (Hukulla) inline screen — screen code, an SBOM, or a container image for threat signatures. Calls the live a11oy immune organ POST /api/a11oy/v1/immune/verdict (the screen IS the signed verdict route). (Renamed 2026-06-16 from the retired codename tool; see DEPRECATED.md.)
Show 11 more tools
szl_khipu_verifyVerify a Khipu receipt hash (+ optional merkle proof) on a flagship. Calls <flagship> POST /khipu/verify.
szl_killinchu_cueGenerate a signed Ballistic-of-Effect (BoE) target cue package. STATE-CHANGING: requires a 2-person Yuyay gate (provide X-Second-Approver). Calls killinchu POST /v1/cue.
szl_killinchu_detectDetect/identify a drone or track from RF signature, Remote-ID, or ADS-B. Calls killinchu POST /counter-uas/identify.
szl_lambda_quorumGovernance-critical Λ verdict under a Byzantine n>=3f+1 quorum (n=5, f=1). Fans the action out to the five SZL organs' policy/verdict routes, collects each organ's verdict, and decides only if >= 2f+1 (=3) reachable organs AGREE and >= 3f+1 (=4) organs are reachable. Each organ's contribution mints a Khipu receipt; the participating receipts are BLS-aggregated into one signature. The full quorum tally + aggregate ride in `governance.quorum`. HONEST: each organ's reachability is captured from the real HTTP status; any organ whose policy route is not live contributes an honest miss and the degr…
szl_lean_verifyVerify a Lean theorem against the live lutar-lean kernel. Calls lean-kernel POST /lean-verify.
szl_puriq_evaluateCompute the PURIQ master operator P(x,t) for an action + return the factor breakdown (Λ, Yuyay-13, HUKLLA, Khipu, Hatun_MCP). Also queries a11oy policy.
szl_thesis_queryRAG query against the thesis-corpus-v18 HF dataset. Calls the a11oy companion grounded-RAG.
szl_wayra_recentRecent WAYRA ingestions. WAYRA agent is not yet deployed — returns an honest 'not yet deployed' payload (disclosed in the receipt, never faked).
szl_yachay_dome_predictYachay-Dome impact prediction for a track over a horizon. Calls killinchu POST /v1/predict-impact.
szl_yuyay_scoreReturn the 13-axis Yuyay breakdown of any content (the heart's scoring).
yuyay_gate_checkRun the 13-axis Yuyay gate over `input` (input-as-data defense). Returns the per-axis verdicts, the Lambda contribution (0/1 conjunctive AND), and a Khipu receipt. axes_to_run optionally restricts which axes are reported (the gate itself always evaluates all 13; this only filters the report).
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit
- Oct 22, 2026 (10 days ago)
- Last release
- Oct 1, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- Registry name
io.github.szl-holdings/hatun-mcp- Version
- 1.0.1
- Auth
- API key
- Packages
- oci
ghcr.io/szl-holdings/hatun-mcp:1.0.1 - License
- Apache-2.0
- Repository
- github.com/szl-holdings/hatun-mcp
- Website
- a-11-oy.com/wires
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
More from szl-holdings
- 0.570score
szl-osf-registration-witness
szl-holdings
Checks a public OSF registration, its attached plan bytes and DataCite DOI with bounded keyless reads.
SkillAFreshness: AClaude Code +9 - 0.570score
szl-analysis-plan-audit
szl-holdings
Compares a frozen analysis plan (primary metric and direction, estimand, sampling and group units, split digest, multiplicity allocation, practical margin…
SkillAFreshness: AClaude Code +9 - 0.570score
szl-artifact-lineage
szl-holdings
Audits the provenance chain of a result: every source, intermediate and output artifact as a versioned id, each transformation's required inputs and stages…
SkillAFreshness: AClaude Code +9 - 0.570score
szl-assay-measurement-audit
szl-holdings
Audits one declared increasing linear laboratory assay run before reporting sample concentrations: separately identified blank and QC wells, calibration…
SkillAFreshness: AClaude Code +9 - 0.570score
szl-clustered-replication
szl-holdings
Audit paired model, assay or pipeline losses when many observations belong to a few independent donors, plates, sites or training runs.
SkillAFreshness: AClaude Code +9 - 0.570score
szl-analysis-mutation-test
szl-holdings
Mutation testing for a data pipeline's quality checks: generates deliberately corrupted copies of a dataset (duplicated samples, dropped rows, shuffled…
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get Hatun MCP - Governed Agent Gateway running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
Hatun MCP - Governed Agent Gateway. Agent Mart. https://agentmart.dev/connectors/szl-holdings-hatun-mcp (last updated 2026-10-24)