geoharness
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
geoharness
Verifiable execution for geospatial agents. geoharness is an MCP server that lets any LLM
agent plan a geospatial workflow as an operator DAG, then statically verifies that plan against
geo-typed operator contracts before anything runs. Failures come back as structured diagnoses
(attribute, required, actual, repairable, repair, hint) that the agent can act on, and only a plan the
server verified (it issues a verified_hash) can be executed. Every call is recorded in a local,
hash-chained provenance ledger.
It is a reference implementation of the GeoAgent specification, supporting a forthcoming standardization effort (a follow-up to ISO/AWI TR 19182). It carries no ISO endorsement.
Status: alpha (0.1.0). APIs, the operator set and file formats may change. Expect rough edges; please read Limitations.
Scope: geoharness verifies and constrains a planner-supplied DAG. It does not search for or synthesize workflows; planning stays with your agent.
Install and run
uvx --from "geoharness[mcp,geo]" geoharness-mcpRequires uv. The mcp extra provides the server, the geo extra (shapely, rasterio, fiona, numpy)
provides real raster/vector IO and execution. Verification-only use works without geo.
Python 3.11-3.13 is covered by CI. The geo extra currently needs Python <= 3.13 (fiona publishes no Python 3.14 wheels; a source build needs GDAL); on 3.14 use geoharness[mcp] for verification only.
Claude Code (plugin)
claude --plugin-dir plugins/claude-code/geoharnessThe plugin bundles the MCP server launcher, the geoharness-workflow skill and local hooks that record
host context next to the ledger. Check it with claude plugin validate plugins/claude-code/geoharness.
See plugins/claude-code/geoharness/README.md.
pi
pi mcp add geoharness -- uvx --from "geoharness[mcp,geo]" geoharness-mcp
mkdir -p ~/.pi/agent/skills && cp -r plugins/pi/skills/geoharness-workflow ~/.pi/agent/skills/See plugins/pi/README.md.
Any other MCP client
Add a stdio server entry:
{
"mcpServers": {
"geoharness": {
"command": "uvx",
"args": ["--from", "geoharness[mcp,geo]", "geoharness-mcp"]
}
}
}Give the agent the protocol from plugins/pi/skills/geoharness-workflow/SKILL.md (plain Markdown).
Without host hooks the exported trace covers the ledger only (coverage: ledger-only).
Related MCP server: MIDAS
The 7 tools
Tool | Purpose |
| Read a raster/vector/table from the workspace; returns an |
| List operator contracts (slots, constraints, parameters, output rules, trust tier). |
| Verify a whole DAG ( |
| Apply the repairable fixes from diagnoses and re-verify. Unrepairable problems are reported, never faked. |
| Run a verified DAG (needs the issued |
| Register a provisional, LLM-authored operator (contract + Python source) behind gates G1-G5. |
| Export the provenance ledger as a zip bundle ( |
There is deliberately no single-operator execution tool: the gate needs the whole DAG.
Protocol: ingest_asset for each input, list_operators, write the WHOLE DAG, verify_dag, repair if
needed, execute_dag. If an operator is missing, tell the user first, then register_operator.
Design details: docs/SPEC.md. Authoring contracts and operators:
docs/AUTHORING.md. JSON Schema of contracts:
geoharness/contracts/schemas/contract-1.0.json.
Privacy
Everything is recorded locally under
<workspace>/.geoharness/(override withGEOHARNESS_HOME; the old nameGEOAGENT_HOMEis still accepted). Nothing is uploaded, ever.The ledger stores paths, sizes and SHA-256 checksums, never your data; secrets and environment values are redacted; chain-of-thought is never read or stored.
The server needs no LLM API key and makes no network calls of its own.
Research bundle submission
If you want to help evaluate geoharness, export_trace(profile="research") writes a redacted bundle
(absolute paths and usernames stripped) after your agent asks you for annotations and your explicit consent.
Bundles land in .geoharness/exports/. Sharing is manual: you decide whether and where to send a bundle;
the server never uploads anything. Review the zip before sharing it.
Limitations
The sandbox is defence in depth, not a security boundary. Provisional operators run Python written by an LLM in a restricted child process (AST scan, import whitelist, audit hook, timeouts, size and memory caps). There are no OS-level namespaces or seccomp; native code in whitelisted libraries is invisible to the audit hook. Only register operators you are comfortable running; they are flagged "LLM-authored, unreviewed".
Trace replay does not support provisional operators (
python -m geoharness.mcp.trace replay).Large rasters cross the sandbox boundary as JSON, so provisional operators on big rasters are slow and memory-hungry.
Alpha: the built-in library is 25 operators; many common GIS operations are not yet covered (see
docs/OPERATOR_AUDIT.md, written in Chinese).The verifier is static (L1-L3) plus runtime post-checks (L4); it checks declared contracts, not the scientific appropriateness of an analysis.
Development
uv sync --extra mcp --extra geo --extra dev
uv run pytest -qSee CONTRIBUTING.md. License: Apache-2.0.
中文说明
geoharness:面向地理空间智能体的“先验证、后执行”框架。
geoharness 是一个 MCP 服务器。任何 LLM 智能体可以把地理空间分析写成算子 DAG,由 geoharness 在执行之前
依据带地理类型的算子契约对其做静态验证;失败时返回结构化诊断(属性、要求、实际值、可否修复、修复方案、提示),
而不是一个布尔值。只有通过验证、并由服务器签发了 verified_hash 的 DAG 才能被执行。每次调用都会写入本地、
哈希链接的溯源账本。
它是 GeoAgent 规范的参考实现,用于支持一项即将开展的标准化工作(ISO/AWI TR 19182 的后续工作), 不代表获得 ISO 的认可。
状态:alpha(0.1.0)。 接口、算子集合和文件格式都可能变化,请先阅读下面的“局限”。
范围:geoharness 只验证、约束由规划器给出的 DAG,不负责搜索或合成工作流;规划由你的智能体完成。
安装与运行
uvx --from "geoharness[mcp,geo]" geoharness-mcp需要 uv。mcp 额外依赖提供服务器,geo(shapely、rasterio、fiona、numpy)提供真实的栅格/矢量读写与执行;
只做验证时可不装 geo。
Claude Code(插件):
claude --plugin-dir plugins/claude-code/geoharness,可用claude plugin validate plugins/claude-code/geoharness校验。pi:
pi mcp add geoharness -- uvx --from "geoharness[mcp,geo]" geoharness-mcp,并把plugins/pi/skills/geoharness-workflow复制到~/.pi/agent/skills/。其他 MCP 客户端:按上文 JSON 添加 stdio 服务器,并把 skill 文本交给智能体作为协议说明。
七个工具
ingest_asset(读入数据并签发 asset_id)、list_operators(列出算子契约)、verify_dag(验证整个 DAG)、
apply_repairs(应用可修复项并重新验证)、execute_dag(执行已验证的 DAG)、register_operator
(注册 LLM 编写的临时算子,需通过 G1-G5 五道关卡)、export_trace(导出溯源包)。
刻意不提供“单算子执行”工具:闸门需要完整的 DAG。
隐私
所有记录都保存在本地的
<工作区>/.geoharness/(可用GEOHARNESS_HOME修改,旧名GEOAGENT_HOME仍可用)。 任何内容都不会被上传。账本只记录路径、大小和 SHA-256,不复制你的数据;密钥与环境变量值会被脱敏;不读取、不保存思维链。
服务器本身不需要任何 LLM API key,也不主动发起网络请求。
研究用溯源包提交
export_trace(profile="research") 会在智能体向你询问标注内容并获得你明确同意之后,导出脱敏的研究包
(绝对路径、用户名被移除),保存在 .geoharness/exports/。是否提交、提交到哪里完全由你手动决定,服务器不会上传。
分享前请自行检查该 zip。
局限
沙箱只是纵深防御,不是安全边界。 临时算子运行的是 LLM 编写的 Python,只在受限子进程中执行(AST 扫描、 导入白名单、审计钩子、超时与内存限制),没有操作系统级隔离。请只注册你愿意运行的算子。
溯源包重放不支持临时(provisional)算子。
大栅格以 JSON 形式穿过沙箱边界,临时算子处理大栅格会很慢、占内存。
alpha 阶段:内置 25 个算子,许多常见 GIS 操作尚未覆盖(见
docs/OPERATOR_AUDIT.md)。验证器检查的是已声明的契约,不判断分析方法在科学上是否合适。
许可证:Apache-2.0。
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
AI-native programming language and toolchain for accountable, verifiable agent-driven development.
Pre-execution governance for AI agents. Deterministic PASS/FAIL/REVIEW verdicts, replayable proof.
Issue & verify signed (ed25519), hash-chained, timestamped provenance receipts for agent actions.
Scoped agent execution. Server-side credentials, policy, budgets and verifiable receipts.
Related MCP Servers
- FlicenseNot gradedqualityBmaintenanceEnables AI coding agents to execute formal, stateful workflows with typed contracts, postcondition enforcement, and structured retry logic.2-
- AlicenseNot gradedqualityCmaintenanceLocal-first AI agent for approval-gated automation and verifiable LLM workflows.1MIT

MapSmithofficial
AlicenseAqualityBmaintenanceEnables AI agents to perform professional-grade geoprocessing tasks such as buffers, overlays, reprojections, and terrain analysis with deterministic tools and verifiable provenance.29273 PyPI2AGPL 3.0- FlicenseBqualityDmaintenanceEnables AI coding assistants to run a machine-verified DESIGN→PLAN→EXECUTE→VERIFY→COMPLETE workflow with human approval gates, state integrity checks, and DAG task scheduling.7-